github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14231] Image generation issue on Tahoe 26.3 (mlx runner failed) #55778

New Issue
Closed
opened 2026-04-29 09:43:26 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 09:43:26 -05:00
Owner
Copy Link

Originally created by @slyapustin on GitHub (Feb 13, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14231

Originally assigned to: @pdevine on GitHub.

What is the issue?

Not sure if it's relevant to the recent Ollama update or MacOS update, but I notice it after both of them got updated.
It was working fine before.

sergey@Ultra ~ % ollama run x/z-image-turbo "a simple photo of an orange on a table"

Error: 500 Internal Server Error: mlx runner failed:   model.norm.weight (exit: exit status 1)

Relevant log output

time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.18.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.18.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.18.mlp.gate_proj: failed to load quantized weight model.layers.18.mlp.gate_proj: tensor \"model.layers.18.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.18.mlp.up_proj: failed to load quantized weight model.layers.18.mlp.up_proj: tensor \"model.layers.18.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.18.mlp.down_proj: failed to load quantized weight model.layers.18.mlp.down_proj: tensor \"model.layers.18.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.18.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.18.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.self_attn.q_proj: failed to load quantized weight model.layers.19.self_attn.q_proj: tensor \"model.layers.19.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.self_attn.k_proj: failed to load quantized weight model.layers.19.self_attn.k_proj: tensor \"model.layers.19.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.self_attn.v_proj: failed to load quantized weight model.layers.19.self_attn.v_proj: tensor \"model.layers.19.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.self_attn.o_proj: failed to load quantized weight model.layers.19.self_attn.o_proj: tensor \"model.layers.19.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.mlp.gate_proj: failed to load quantized weight model.layers.19.mlp.gate_proj: tensor \"model.layers.19.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.mlp.up_proj: failed to load quantized weight model.layers.19.mlp.up_proj: tensor \"model.layers.19.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.mlp.down_proj: failed to load quantized weight model.layers.19.mlp.down_proj: tensor \"model.layers.19.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.19.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.self_attn.q_proj: failed to load quantized weight model.layers.20.self_attn.q_proj: tensor \"model.layers.20.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.self_attn.k_proj: failed to load quantized weight model.layers.20.self_attn.k_proj: tensor \"model.layers.20.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.self_attn.v_proj: failed to load quantized weight model.layers.20.self_attn.v_proj: tensor \"model.layers.20.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.self_attn.o_proj: failed to load quantized weight model.layers.20.self_attn.o_proj: tensor \"model.layers.20.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.mlp.gate_proj: failed to load quantized weight model.layers.20.mlp.gate_proj: tensor \"model.layers.20.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.mlp.up_proj: failed to load quantized weight model.layers.20.mlp.up_proj: tensor \"model.layers.20.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.mlp.down_proj: failed to load quantized weight model.layers.20.mlp.down_proj: tensor \"model.layers.20.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.20.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.self_attn.q_proj: failed to load quantized weight model.layers.21.self_attn.q_proj: tensor \"model.layers.21.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.self_attn.k_proj: failed to load quantized weight model.layers.21.self_attn.k_proj: tensor \"model.layers.21.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.self_attn.v_proj: failed to load quantized weight model.layers.21.self_attn.v_proj: tensor \"model.layers.21.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.self_attn.o_proj: failed to load quantized weight model.layers.21.self_attn.o_proj: tensor \"model.layers.21.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.mlp.gate_proj: failed to load quantized weight model.layers.21.mlp.gate_proj: tensor \"model.layers.21.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.mlp.up_proj: failed to load quantized weight model.layers.21.mlp.up_proj: tensor \"model.layers.21.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.mlp.down_proj: failed to load quantized weight model.layers.21.mlp.down_proj: tensor \"model.layers.21.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.21.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.self_attn.q_proj: failed to load quantized weight model.layers.22.self_attn.q_proj: tensor \"model.layers.22.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.self_attn.k_proj: failed to load quantized weight model.layers.22.self_attn.k_proj: tensor \"model.layers.22.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.self_attn.v_proj: failed to load quantized weight model.layers.22.self_attn.v_proj: tensor \"model.layers.22.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.self_attn.o_proj: failed to load quantized weight model.layers.22.self_attn.o_proj: tensor \"model.layers.22.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.mlp.gate_proj: failed to load quantized weight model.layers.22.mlp.gate_proj: tensor \"model.layers.22.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.mlp.up_proj: failed to load quantized weight model.layers.22.mlp.up_proj: tensor \"model.layers.22.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.mlp.down_proj: failed to load quantized weight model.layers.22.mlp.down_proj: tensor \"model.layers.22.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.22.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.self_attn.q_proj: failed to load quantized weight model.layers.23.self_attn.q_proj: tensor \"model.layers.23.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.self_attn.k_proj: failed to load quantized weight model.layers.23.self_attn.k_proj: tensor \"model.layers.23.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.self_attn.v_proj: failed to load quantized weight model.layers.23.self_attn.v_proj: tensor \"model.layers.23.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.self_attn.o_proj: failed to load quantized weight model.layers.23.self_attn.o_proj: tensor \"model.layers.23.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.mlp.gate_proj: failed to load quantized weight model.layers.23.mlp.gate_proj: tensor \"model.layers.23.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.mlp.up_proj: failed to load quantized weight model.layers.23.mlp.up_proj: tensor \"model.layers.23.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.mlp.down_proj: failed to load quantized weight model.layers.23.mlp.down_proj: tensor \"model.layers.23.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.23.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.self_attn.q_proj: failed to load quantized weight model.layers.24.self_attn.q_proj: tensor \"model.layers.24.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.self_attn.k_proj: failed to load quantized weight model.layers.24.self_attn.k_proj: tensor \"model.layers.24.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.self_attn.v_proj: failed to load quantized weight model.layers.24.self_attn.v_proj: tensor \"model.layers.24.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.self_attn.o_proj: failed to load quantized weight model.layers.24.self_attn.o_proj: tensor \"model.layers.24.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.mlp.gate_proj: failed to load quantized weight model.layers.24.mlp.gate_proj: tensor \"model.layers.24.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.mlp.up_proj: failed to load quantized weight model.layers.24.mlp.up_proj: tensor \"model.layers.24.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.mlp.down_proj: failed to load quantized weight model.layers.24.mlp.down_proj: tensor \"model.layers.24.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.24.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.self_attn.q_proj: failed to load quantized weight model.layers.25.self_attn.q_proj: tensor \"model.layers.25.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.self_attn.k_proj: failed to load quantized weight model.layers.25.self_attn.k_proj: tensor \"model.layers.25.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.self_attn.v_proj: failed to load quantized weight model.layers.25.self_attn.v_proj: tensor \"model.layers.25.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.self_attn.o_proj: failed to load quantized weight model.layers.25.self_attn.o_proj: tensor \"model.layers.25.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.mlp.gate_proj: failed to load quantized weight model.layers.25.mlp.gate_proj: tensor \"model.layers.25.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.mlp.up_proj: failed to load quantized weight model.layers.25.mlp.up_proj: tensor \"model.layers.25.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.mlp.down_proj: failed to load quantized weight model.layers.25.mlp.down_proj: tensor \"model.layers.25.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.25.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.self_attn.q_proj: failed to load quantized weight model.layers.26.self_attn.q_proj: tensor \"model.layers.26.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.self_attn.k_proj: failed to load quantized weight model.layers.26.self_attn.k_proj: tensor \"model.layers.26.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.self_attn.v_proj: failed to load quantized weight model.layers.26.self_attn.v_proj: tensor \"model.layers.26.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.self_attn.o_proj: failed to load quantized weight model.layers.26.self_attn.o_proj: tensor \"model.layers.26.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.mlp.gate_proj: failed to load quantized weight model.layers.26.mlp.gate_proj: tensor \"model.layers.26.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.mlp.up_proj: failed to load quantized weight model.layers.26.mlp.up_proj: tensor \"model.layers.26.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.mlp.down_proj: failed to load quantized weight model.layers.26.mlp.down_proj: tensor \"model.layers.26.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.26.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.self_attn.q_proj: failed to load quantized weight model.layers.27.self_attn.q_proj: tensor \"model.layers.27.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.self_attn.k_proj: failed to load quantized weight model.layers.27.self_attn.k_proj: tensor \"model.layers.27.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.self_attn.v_proj: failed to load quantized weight model.layers.27.self_attn.v_proj: tensor \"model.layers.27.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.self_attn.o_proj: failed to load quantized weight model.layers.27.self_attn.o_proj: tensor \"model.layers.27.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.mlp.gate_proj: failed to load quantized weight model.layers.27.mlp.gate_proj: tensor \"model.layers.27.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.mlp.up_proj: failed to load quantized weight model.layers.27.mlp.up_proj: tensor \"model.layers.27.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.mlp.down_proj: failed to load quantized weight model.layers.27.mlp.down_proj: tensor \"model.layers.27.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.27.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.self_attn.q_proj: failed to load quantized weight model.layers.28.self_attn.q_proj: tensor \"model.layers.28.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.self_attn.k_proj: failed to load quantized weight model.layers.28.self_attn.k_proj: tensor \"model.layers.28.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.self_attn.v_proj: failed to load quantized weight model.layers.28.self_attn.v_proj: tensor \"model.layers.28.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.self_attn.o_proj: failed to load quantized weight model.layers.28.self_attn.o_proj: tensor \"model.layers.28.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.mlp.gate_proj: failed to load quantized weight model.layers.28.mlp.gate_proj: tensor \"model.layers.28.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.mlp.up_proj: failed to load quantized weight model.layers.28.mlp.up_proj: tensor \"model.layers.28.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.mlp.down_proj: failed to load quantized weight model.layers.28.mlp.down_proj: tensor \"model.layers.28.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.28.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.self_attn.q_proj: failed to load quantized weight model.layers.29.self_attn.q_proj: tensor \"model.layers.29.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.self_attn.k_proj: failed to load quantized weight model.layers.29.self_attn.k_proj: tensor \"model.layers.29.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.self_attn.v_proj: failed to load quantized weight model.layers.29.self_attn.v_proj: tensor \"model.layers.29.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.self_attn.o_proj: failed to load quantized weight model.layers.29.self_attn.o_proj: tensor \"model.layers.29.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.mlp.gate_proj: failed to load quantized weight model.layers.29.mlp.gate_proj: tensor \"model.layers.29.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.mlp.up_proj: failed to load quantized weight model.layers.29.mlp.up_proj: tensor \"model.layers.29.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.mlp.down_proj: failed to load quantized weight model.layers.29.mlp.down_proj: tensor \"model.layers.29.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.29.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.self_attn.q_proj: failed to load quantized weight model.layers.30.self_attn.q_proj: tensor \"model.layers.30.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.self_attn.k_proj: failed to load quantized weight model.layers.30.self_attn.k_proj: tensor \"model.layers.30.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.self_attn.v_proj: failed to load quantized weight model.layers.30.self_attn.v_proj: tensor \"model.layers.30.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.self_attn.o_proj: failed to load quantized weight model.layers.30.self_attn.o_proj: tensor \"model.layers.30.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.mlp.gate_proj: failed to load quantized weight model.layers.30.mlp.gate_proj: tensor \"model.layers.30.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.mlp.up_proj: failed to load quantized weight model.layers.30.mlp.up_proj: tensor \"model.layers.30.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.mlp.down_proj: failed to load quantized weight model.layers.30.mlp.down_proj: tensor \"model.layers.30.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.input_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.30.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.self_attn.q_proj: failed to load quantized weight model.layers.31.self_attn.q_proj: tensor \"model.layers.31.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.self_attn.k_proj: failed to load quantized weight model.layers.31.self_attn.k_proj: tensor \"model.layers.31.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.self_attn.v_proj: failed to load quantized weight model.layers.31.self_attn.v_proj: tensor \"model.layers.31.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.self_attn.o_proj: failed to load quantized weight model.layers.31.self_attn.o_proj: tensor \"model.layers.31.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.mlp.gate_proj: failed to load quantized weight model.layers.31.mlp.gate_proj: tensor \"model.layers.31.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.mlp.up_proj: failed to load quantized weight model.layers.31.mlp.up_proj: tensor \"model.layers.31.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.mlp.down_proj: failed to load quantized weight model.layers.31.mlp.down_proj: tensor \"model.layers.31.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.input_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.31.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.self_attn.q_proj: failed to load quantized weight model.layers.32.self_attn.q_proj: tensor \"model.layers.32.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.self_attn.k_proj: failed to load quantized weight model.layers.32.self_attn.k_proj: tensor \"model.layers.32.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.self_attn.v_proj: failed to load quantized weight model.layers.32.self_attn.v_proj: tensor \"model.layers.32.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.self_attn.o_proj: failed to load quantized weight model.layers.32.self_attn.o_proj: tensor \"model.layers.32.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.mlp.gate_proj: failed to load quantized weight model.layers.32.mlp.gate_proj: tensor \"model.layers.32.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.mlp.up_proj: failed to load quantized weight model.layers.32.mlp.up_proj: tensor \"model.layers.32.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.mlp.down_proj: failed to load quantized weight model.layers.32.mlp.down_proj: tensor \"model.layers.32.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.input_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.32.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.self_attn.q_proj: failed to load quantized weight model.layers.33.self_attn.q_proj: tensor \"model.layers.33.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.self_attn.k_proj: failed to load quantized weight model.layers.33.self_attn.k_proj: tensor \"model.layers.33.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.self_attn.v_proj: failed to load quantized weight model.layers.33.self_attn.v_proj: tensor \"model.layers.33.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.self_attn.o_proj: failed to load quantized weight model.layers.33.self_attn.o_proj: tensor \"model.layers.33.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.mlp.gate_proj: failed to load quantized weight model.layers.33.mlp.gate_proj: tensor \"model.layers.33.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.mlp.up_proj: failed to load quantized weight model.layers.33.mlp.up_proj: tensor \"model.layers.33.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.mlp.down_proj: failed to load quantized weight model.layers.33.mlp.down_proj: tensor \"model.layers.33.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.input_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.33.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.self_attn.q_proj: failed to load quantized weight model.layers.34.self_attn.q_proj: tensor \"model.layers.34.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.self_attn.k_proj: failed to load quantized weight model.layers.34.self_attn.k_proj: tensor \"model.layers.34.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.self_attn.v_proj: failed to load quantized weight model.layers.34.self_attn.v_proj: tensor \"model.layers.34.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.self_attn.o_proj: failed to load quantized weight model.layers.34.self_attn.o_proj: tensor \"model.layers.34.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.mlp.gate_proj: failed to load quantized weight model.layers.34.mlp.gate_proj: tensor \"model.layers.34.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.mlp.up_proj: failed to load quantized weight model.layers.34.mlp.up_proj: tensor \"model.layers.34.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.mlp.down_proj: failed to load quantized weight model.layers.34.mlp.down_proj: tensor \"model.layers.34.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.input_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.34.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.self_attn.q_proj: failed to load quantized weight model.layers.35.self_attn.q_proj: tensor \"model.layers.35.self_attn.q_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.self_attn.k_proj: failed to load quantized weight model.layers.35.self_attn.k_proj: tensor \"model.layers.35.self_attn.k_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.self_attn.v_proj: failed to load quantized weight model.layers.35.self_attn.v_proj: tensor \"model.layers.35.self_attn.v_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.self_attn.o_proj: failed to load quantized weight model.layers.35.self_attn.o_proj: tensor \"model.layers.35.self_attn.o_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.self_attn.q_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.self_attn.k_norm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.mlp.gate_proj: failed to load quantized weight model.layers.35.mlp.gate_proj: tensor \"model.layers.35.mlp.gate_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.mlp.up_proj: failed to load quantized weight model.layers.35.mlp.up_proj: tensor \"model.layers.35.mlp.up_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.mlp.down_proj: failed to load quantized weight model.layers.35.mlp.down_proj: tensor \"model.layers.35.mlp.down_proj.weight\" not found"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.input_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.layers.35.post_attention_layernorm.weight"
time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg="  model.norm.weight"
time=2026-02-13T10:27:29.637+01:00 level=INFO source=server.go:134 msg=mlx-runner msg="  Loading text encoder... "
time=2026-02-13T10:27:29.637+01:00 level=INFO source=server.go:363 msg="stopping mlx runner subprocess" pid=72545
[GIN] 2026/02/13 - 10:27:34 | 500 |  5.958062833s |       127.0.0.1 | POST     "/api/generate"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.16.1

Originally created by @slyapustin on GitHub (Feb 13, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14231 Originally assigned to: @pdevine on GitHub. ### What is the issue? Not sure if it's relevant to the recent Ollama update or MacOS update, but I notice it after both of them got updated. It was working fine before. ``` sergey@Ultra ~ % ollama run x/z-image-turbo "a simple photo of an orange on a table" Error: 500 Internal Server Error: mlx runner failed: model.norm.weight (exit: exit status 1) ``` ### Relevant log output ```shell time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.18.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.18.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.18.mlp.gate_proj: failed to load quantized weight model.layers.18.mlp.gate_proj: tensor \"model.layers.18.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.18.mlp.up_proj: failed to load quantized weight model.layers.18.mlp.up_proj: tensor \"model.layers.18.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.18.mlp.down_proj: failed to load quantized weight model.layers.18.mlp.down_proj: tensor \"model.layers.18.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.18.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.18.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.self_attn.q_proj: failed to load quantized weight model.layers.19.self_attn.q_proj: tensor \"model.layers.19.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.self_attn.k_proj: failed to load quantized weight model.layers.19.self_attn.k_proj: tensor \"model.layers.19.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.self_attn.v_proj: failed to load quantized weight model.layers.19.self_attn.v_proj: tensor \"model.layers.19.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.self_attn.o_proj: failed to load quantized weight model.layers.19.self_attn.o_proj: tensor \"model.layers.19.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.mlp.gate_proj: failed to load quantized weight model.layers.19.mlp.gate_proj: tensor \"model.layers.19.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.mlp.up_proj: failed to load quantized weight model.layers.19.mlp.up_proj: tensor \"model.layers.19.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.mlp.down_proj: failed to load quantized weight model.layers.19.mlp.down_proj: tensor \"model.layers.19.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.19.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.self_attn.q_proj: failed to load quantized weight model.layers.20.self_attn.q_proj: tensor \"model.layers.20.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.self_attn.k_proj: failed to load quantized weight model.layers.20.self_attn.k_proj: tensor \"model.layers.20.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.self_attn.v_proj: failed to load quantized weight model.layers.20.self_attn.v_proj: tensor \"model.layers.20.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.self_attn.o_proj: failed to load quantized weight model.layers.20.self_attn.o_proj: tensor \"model.layers.20.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.mlp.gate_proj: failed to load quantized weight model.layers.20.mlp.gate_proj: tensor \"model.layers.20.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.mlp.up_proj: failed to load quantized weight model.layers.20.mlp.up_proj: tensor \"model.layers.20.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.mlp.down_proj: failed to load quantized weight model.layers.20.mlp.down_proj: tensor \"model.layers.20.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.20.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.self_attn.q_proj: failed to load quantized weight model.layers.21.self_attn.q_proj: tensor \"model.layers.21.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.self_attn.k_proj: failed to load quantized weight model.layers.21.self_attn.k_proj: tensor \"model.layers.21.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.self_attn.v_proj: failed to load quantized weight model.layers.21.self_attn.v_proj: tensor \"model.layers.21.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.self_attn.o_proj: failed to load quantized weight model.layers.21.self_attn.o_proj: tensor \"model.layers.21.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.mlp.gate_proj: failed to load quantized weight model.layers.21.mlp.gate_proj: tensor \"model.layers.21.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.mlp.up_proj: failed to load quantized weight model.layers.21.mlp.up_proj: tensor \"model.layers.21.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.mlp.down_proj: failed to load quantized weight model.layers.21.mlp.down_proj: tensor \"model.layers.21.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.21.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.self_attn.q_proj: failed to load quantized weight model.layers.22.self_attn.q_proj: tensor \"model.layers.22.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.self_attn.k_proj: failed to load quantized weight model.layers.22.self_attn.k_proj: tensor \"model.layers.22.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.self_attn.v_proj: failed to load quantized weight model.layers.22.self_attn.v_proj: tensor \"model.layers.22.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.self_attn.o_proj: failed to load quantized weight model.layers.22.self_attn.o_proj: tensor \"model.layers.22.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.mlp.gate_proj: failed to load quantized weight model.layers.22.mlp.gate_proj: tensor \"model.layers.22.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.mlp.up_proj: failed to load quantized weight model.layers.22.mlp.up_proj: tensor \"model.layers.22.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.mlp.down_proj: failed to load quantized weight model.layers.22.mlp.down_proj: tensor \"model.layers.22.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.22.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.self_attn.q_proj: failed to load quantized weight model.layers.23.self_attn.q_proj: tensor \"model.layers.23.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.self_attn.k_proj: failed to load quantized weight model.layers.23.self_attn.k_proj: tensor \"model.layers.23.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.self_attn.v_proj: failed to load quantized weight model.layers.23.self_attn.v_proj: tensor \"model.layers.23.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.self_attn.o_proj: failed to load quantized weight model.layers.23.self_attn.o_proj: tensor \"model.layers.23.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.mlp.gate_proj: failed to load quantized weight model.layers.23.mlp.gate_proj: tensor \"model.layers.23.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.mlp.up_proj: failed to load quantized weight model.layers.23.mlp.up_proj: tensor \"model.layers.23.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.mlp.down_proj: failed to load quantized weight model.layers.23.mlp.down_proj: tensor \"model.layers.23.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.23.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.self_attn.q_proj: failed to load quantized weight model.layers.24.self_attn.q_proj: tensor \"model.layers.24.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.self_attn.k_proj: failed to load quantized weight model.layers.24.self_attn.k_proj: tensor \"model.layers.24.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.self_attn.v_proj: failed to load quantized weight model.layers.24.self_attn.v_proj: tensor \"model.layers.24.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.self_attn.o_proj: failed to load quantized weight model.layers.24.self_attn.o_proj: tensor \"model.layers.24.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.mlp.gate_proj: failed to load quantized weight model.layers.24.mlp.gate_proj: tensor \"model.layers.24.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.mlp.up_proj: failed to load quantized weight model.layers.24.mlp.up_proj: tensor \"model.layers.24.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.mlp.down_proj: failed to load quantized weight model.layers.24.mlp.down_proj: tensor \"model.layers.24.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.24.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.self_attn.q_proj: failed to load quantized weight model.layers.25.self_attn.q_proj: tensor \"model.layers.25.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.self_attn.k_proj: failed to load quantized weight model.layers.25.self_attn.k_proj: tensor \"model.layers.25.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.self_attn.v_proj: failed to load quantized weight model.layers.25.self_attn.v_proj: tensor \"model.layers.25.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.self_attn.o_proj: failed to load quantized weight model.layers.25.self_attn.o_proj: tensor \"model.layers.25.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.mlp.gate_proj: failed to load quantized weight model.layers.25.mlp.gate_proj: tensor \"model.layers.25.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.mlp.up_proj: failed to load quantized weight model.layers.25.mlp.up_proj: tensor \"model.layers.25.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.mlp.down_proj: failed to load quantized weight model.layers.25.mlp.down_proj: tensor \"model.layers.25.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.25.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.self_attn.q_proj: failed to load quantized weight model.layers.26.self_attn.q_proj: tensor \"model.layers.26.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.self_attn.k_proj: failed to load quantized weight model.layers.26.self_attn.k_proj: tensor \"model.layers.26.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.self_attn.v_proj: failed to load quantized weight model.layers.26.self_attn.v_proj: tensor \"model.layers.26.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.self_attn.o_proj: failed to load quantized weight model.layers.26.self_attn.o_proj: tensor \"model.layers.26.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.mlp.gate_proj: failed to load quantized weight model.layers.26.mlp.gate_proj: tensor \"model.layers.26.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.mlp.up_proj: failed to load quantized weight model.layers.26.mlp.up_proj: tensor \"model.layers.26.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.mlp.down_proj: failed to load quantized weight model.layers.26.mlp.down_proj: tensor \"model.layers.26.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.26.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.self_attn.q_proj: failed to load quantized weight model.layers.27.self_attn.q_proj: tensor \"model.layers.27.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.self_attn.k_proj: failed to load quantized weight model.layers.27.self_attn.k_proj: tensor \"model.layers.27.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.self_attn.v_proj: failed to load quantized weight model.layers.27.self_attn.v_proj: tensor \"model.layers.27.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.self_attn.o_proj: failed to load quantized weight model.layers.27.self_attn.o_proj: tensor \"model.layers.27.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.mlp.gate_proj: failed to load quantized weight model.layers.27.mlp.gate_proj: tensor \"model.layers.27.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.mlp.up_proj: failed to load quantized weight model.layers.27.mlp.up_proj: tensor \"model.layers.27.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.mlp.down_proj: failed to load quantized weight model.layers.27.mlp.down_proj: tensor \"model.layers.27.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.27.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.self_attn.q_proj: failed to load quantized weight model.layers.28.self_attn.q_proj: tensor \"model.layers.28.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.self_attn.k_proj: failed to load quantized weight model.layers.28.self_attn.k_proj: tensor \"model.layers.28.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.self_attn.v_proj: failed to load quantized weight model.layers.28.self_attn.v_proj: tensor \"model.layers.28.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.self_attn.o_proj: failed to load quantized weight model.layers.28.self_attn.o_proj: tensor \"model.layers.28.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.mlp.gate_proj: failed to load quantized weight model.layers.28.mlp.gate_proj: tensor \"model.layers.28.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.mlp.up_proj: failed to load quantized weight model.layers.28.mlp.up_proj: tensor \"model.layers.28.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.mlp.down_proj: failed to load quantized weight model.layers.28.mlp.down_proj: tensor \"model.layers.28.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.28.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.self_attn.q_proj: failed to load quantized weight model.layers.29.self_attn.q_proj: tensor \"model.layers.29.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.self_attn.k_proj: failed to load quantized weight model.layers.29.self_attn.k_proj: tensor \"model.layers.29.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.self_attn.v_proj: failed to load quantized weight model.layers.29.self_attn.v_proj: tensor \"model.layers.29.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.self_attn.o_proj: failed to load quantized weight model.layers.29.self_attn.o_proj: tensor \"model.layers.29.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.mlp.gate_proj: failed to load quantized weight model.layers.29.mlp.gate_proj: tensor \"model.layers.29.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.mlp.up_proj: failed to load quantized weight model.layers.29.mlp.up_proj: tensor \"model.layers.29.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.mlp.down_proj: failed to load quantized weight model.layers.29.mlp.down_proj: tensor \"model.layers.29.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.29.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.self_attn.q_proj: failed to load quantized weight model.layers.30.self_attn.q_proj: tensor \"model.layers.30.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.self_attn.k_proj: failed to load quantized weight model.layers.30.self_attn.k_proj: tensor \"model.layers.30.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.self_attn.v_proj: failed to load quantized weight model.layers.30.self_attn.v_proj: tensor \"model.layers.30.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.self_attn.o_proj: failed to load quantized weight model.layers.30.self_attn.o_proj: tensor \"model.layers.30.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.self_attn.q_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.self_attn.k_norm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.mlp.gate_proj: failed to load quantized weight model.layers.30.mlp.gate_proj: tensor \"model.layers.30.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.mlp.up_proj: failed to load quantized weight model.layers.30.mlp.up_proj: tensor \"model.layers.30.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.mlp.down_proj: failed to load quantized weight model.layers.30.mlp.down_proj: tensor \"model.layers.30.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.input_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.30.post_attention_layernorm.weight" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.self_attn.q_proj: failed to load quantized weight model.layers.31.self_attn.q_proj: tensor \"model.layers.31.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.553+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.self_attn.k_proj: failed to load quantized weight model.layers.31.self_attn.k_proj: tensor \"model.layers.31.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.self_attn.v_proj: failed to load quantized weight model.layers.31.self_attn.v_proj: tensor \"model.layers.31.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.self_attn.o_proj: failed to load quantized weight model.layers.31.self_attn.o_proj: tensor \"model.layers.31.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.self_attn.q_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.self_attn.k_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.mlp.gate_proj: failed to load quantized weight model.layers.31.mlp.gate_proj: tensor \"model.layers.31.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.mlp.up_proj: failed to load quantized weight model.layers.31.mlp.up_proj: tensor \"model.layers.31.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.mlp.down_proj: failed to load quantized weight model.layers.31.mlp.down_proj: tensor \"model.layers.31.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.input_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.31.post_attention_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.self_attn.q_proj: failed to load quantized weight model.layers.32.self_attn.q_proj: tensor \"model.layers.32.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.self_attn.k_proj: failed to load quantized weight model.layers.32.self_attn.k_proj: tensor \"model.layers.32.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.self_attn.v_proj: failed to load quantized weight model.layers.32.self_attn.v_proj: tensor \"model.layers.32.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.self_attn.o_proj: failed to load quantized weight model.layers.32.self_attn.o_proj: tensor \"model.layers.32.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.self_attn.q_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.self_attn.k_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.mlp.gate_proj: failed to load quantized weight model.layers.32.mlp.gate_proj: tensor \"model.layers.32.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.mlp.up_proj: failed to load quantized weight model.layers.32.mlp.up_proj: tensor \"model.layers.32.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.mlp.down_proj: failed to load quantized weight model.layers.32.mlp.down_proj: tensor \"model.layers.32.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.input_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.32.post_attention_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.self_attn.q_proj: failed to load quantized weight model.layers.33.self_attn.q_proj: tensor \"model.layers.33.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.self_attn.k_proj: failed to load quantized weight model.layers.33.self_attn.k_proj: tensor \"model.layers.33.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.self_attn.v_proj: failed to load quantized weight model.layers.33.self_attn.v_proj: tensor \"model.layers.33.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.self_attn.o_proj: failed to load quantized weight model.layers.33.self_attn.o_proj: tensor \"model.layers.33.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.self_attn.q_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.self_attn.k_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.mlp.gate_proj: failed to load quantized weight model.layers.33.mlp.gate_proj: tensor \"model.layers.33.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.mlp.up_proj: failed to load quantized weight model.layers.33.mlp.up_proj: tensor \"model.layers.33.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.mlp.down_proj: failed to load quantized weight model.layers.33.mlp.down_proj: tensor \"model.layers.33.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.input_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.33.post_attention_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.self_attn.q_proj: failed to load quantized weight model.layers.34.self_attn.q_proj: tensor \"model.layers.34.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.self_attn.k_proj: failed to load quantized weight model.layers.34.self_attn.k_proj: tensor \"model.layers.34.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.self_attn.v_proj: failed to load quantized weight model.layers.34.self_attn.v_proj: tensor \"model.layers.34.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.self_attn.o_proj: failed to load quantized weight model.layers.34.self_attn.o_proj: tensor \"model.layers.34.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.self_attn.q_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.self_attn.k_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.mlp.gate_proj: failed to load quantized weight model.layers.34.mlp.gate_proj: tensor \"model.layers.34.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.mlp.up_proj: failed to load quantized weight model.layers.34.mlp.up_proj: tensor \"model.layers.34.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.mlp.down_proj: failed to load quantized weight model.layers.34.mlp.down_proj: tensor \"model.layers.34.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.input_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.34.post_attention_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.self_attn.q_proj: failed to load quantized weight model.layers.35.self_attn.q_proj: tensor \"model.layers.35.self_attn.q_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.self_attn.k_proj: failed to load quantized weight model.layers.35.self_attn.k_proj: tensor \"model.layers.35.self_attn.k_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.self_attn.v_proj: failed to load quantized weight model.layers.35.self_attn.v_proj: tensor \"model.layers.35.self_attn.v_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.self_attn.o_proj: failed to load quantized weight model.layers.35.self_attn.o_proj: tensor \"model.layers.35.self_attn.o_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.self_attn.q_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.self_attn.k_norm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.mlp.gate_proj: failed to load quantized weight model.layers.35.mlp.gate_proj: tensor \"model.layers.35.mlp.gate_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.mlp.up_proj: failed to load quantized weight model.layers.35.mlp.up_proj: tensor \"model.layers.35.mlp.up_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.mlp.down_proj: failed to load quantized weight model.layers.35.mlp.down_proj: tensor \"model.layers.35.mlp.down_proj.weight\" not found" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.input_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.layers.35.post_attention_layernorm.weight" time=2026-02-13T10:27:29.554+01:00 level=WARN source=server.go:141 msg=mlx-runner msg=" model.norm.weight" time=2026-02-13T10:27:29.637+01:00 level=INFO source=server.go:134 msg=mlx-runner msg=" Loading text encoder... " time=2026-02-13T10:27:29.637+01:00 level=INFO source=server.go:363 msg="stopping mlx runner subprocess" pid=72545 [GIN] 2026/02/13 - 10:27:34 | 500 | 5.958062833s | 127.0.0.1 | POST "/api/generate" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.16.1
GiteaMirror added the bug label 2026-04-29 09:43:26 -05:00
GiteaMirror commented 2026-04-29 09:43:29 -05:00
Author
Owner
Copy Link

@slyapustin commented on GitHub (Feb 13, 2026):

Downgrading back to 0.15.1 seems to have fixed the issue.

<!-- gh-comment-id:3896041018 --> @slyapustin commented on GitHub (Feb 13, 2026): Downgrading back to 0.15.1 seems to have fixed the issue.
GiteaMirror commented 2026-04-29 09:43:30 -05:00
Author
Owner
Copy Link

@dryoo commented on GitHub (Feb 13, 2026):

It was working fine before. can confirm

<!-- gh-comment-id:3897560522 --> @dryoo commented on GitHub (Feb 13, 2026): It was working fine before. can confirm
GiteaMirror commented 2026-04-29 09:43:30 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Feb 14, 2026):

Sorry about this guys. The fix is in for 0.16.2 if you want to try the pre-release.

<!-- gh-comment-id:3902183455 --> @pdevine commented on GitHub (Feb 14, 2026): Sorry about this guys. The fix is in for 0.16.2 if you want to try the pre-release.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#55778
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?