[GH-ISSUE #14133] Qwen3 coder next can't be loaded on 0.15.5 #9219

Closed
opened 2026-04-12 22:04:49 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @xixixihaha on GitHub (Feb 7, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14133

What is the issue?

When we tried to load qwen3-coder-next:q4_K_M and qwen3-coder-next:q8_0, it prompted with
ollama run qwen3-coder-next:q4_K_M
Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.ssm_in.weight'
llama_model_load_from_file_impl: failed to load model

Relevant log output

Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.ssm_in.weight'
llama_model_load_from_file_impl: failed to load model

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.15.5-rc0

Originally created by @xixixihaha on GitHub (Feb 7, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14133 ### What is the issue? When we tried to load qwen3-coder-next:q4_K_M and qwen3-coder-next:q8_0, it prompted with ollama run qwen3-coder-next:q4_K_M Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.ssm_in.weight' llama_model_load_from_file_impl: failed to load model ### Relevant log output ```shell Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.ssm_in.weight' llama_model_load_from_file_impl: failed to load model ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.15.5-rc0
GiteaMirror added the bug label 2026-04-12 22:04:49 -05:00
Author
Owner

@jmorganca commented on GitHub (Feb 7, 2026):

Hi there, please upgrade to 0.15.5 (not RC).

<!-- gh-comment-id:3863434175 --> @jmorganca commented on GitHub (Feb 7, 2026): Hi there, please upgrade to 0.15.5 (not RC).
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9219