github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11000] 0.90 issue with Modelfile #7253

New Issue
Closed
opened 2026-04-12 19:17:57 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 19:17:57 -05:00
Owner
Copy Link

Originally created by @goactiongo on GitHub (Jun 6, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11000

What is the issue?

I create the new model with modelfile edited with following commands:

ollama show qwen3:32b  --modelfile > Modelfile
echo PARAMETER num_predict -1 >> Modelfile
echo PARAMETER num_ctx 125000 >> Modelfile
ollama create qwen3:32b_125k -f Modelfile

Seems that the new model didn't work well with log followed,pls

Image

qwen3_32b.txt
qwen3_32b_numctx125k.txt

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @goactiongo on GitHub (Jun 6, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11000 ### What is the issue? I create the new model with modelfile edited with following commands: ``` ollama show qwen3:32b --modelfile > Modelfile echo PARAMETER num_predict -1 >> Modelfile echo PARAMETER num_ctx 125000 >> Modelfile ollama create qwen3:32b_125k -f Modelfile ``` Seems that the new model didn't work well with log followed,pls ![Image](https://github.com/user-attachments/assets/e6116ec2-3e17-4ec2-81ca-90f5a1332751) [qwen3_32b.txt](https://github.com/user-attachments/files/20633261/qwen3_32b.txt) [qwen3_32b_numctx125k.txt](https://github.com/user-attachments/files/20633260/qwen3_32b_numctx125k.txt) ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 19:17:57 -05:00
GiteaMirror commented 2026-04-12 19:17:58 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 6, 2025):

What does "didn't work well" mean? Didn't answer prompts? Answered incorrectly? Too slow?

<!-- gh-comment-id:2950663242 --> @rick-github commented on GitHub (Jun 6, 2025): What does "didn't work well" mean? Didn't answer prompts? Answered incorrectly? Too slow?
GiteaMirror commented 2026-04-12 19:17:59 -05:00
Author
Owner
Copy Link

@goactiongo commented on GitHub (Jun 6, 2025):

Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: loading model tensors, this can take a while... (mmap = false)
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 0 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 1 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 2 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 3 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 4 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 5 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 6 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 7 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 8 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 9 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 10 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 11 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 12 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 13 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 14 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 15 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 16 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 17 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 18 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 19 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 20 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 21 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 22 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 23 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 24 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 25 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 26 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 27 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 28 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 29 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 30 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 31 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 32 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 33 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 34 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 35 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 36 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 37 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 38 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 39 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 40 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 41 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 42 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 43 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 44 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 45 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 46 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 47 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 48 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 49 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 50 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 51 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 52 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 53 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 54 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 55 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 56 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 57 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 58 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 59 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 60 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 61 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 62 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 63 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 64 assigned to device CPU, is_swa = 0
Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: CPU model buffer size = 19259.71 MiB
Jun 06 19:12:13 ai001 ollama[590926]: load_all_data: no device found for buffer type CPU for async uploads
Jun 06 19:12:13 ai001 ollama[590926]: time=2025-06-06T19:12:13.955Z level=DEBUG source=server.go:636 msg="model load progress 0.02"
Jun 06 19:12:14 ai001 ollama[590926]: time=2025-06-06T19:12:14.205Z level=DEBUG source=server.go:636 msg="model load progress 0.06"
Jun 06 19:12:14 ai001 ollama[590926]: time=2025-06-06T19:12:14.456Z level=DEBUG source=server.go:636 msg="model load progress 0.08"
Jun 06 19:12:14 ai001 ollama[590926]: time=2025-06-06T19:12:14.707Z level=DEBUG source=server.go:636 msg="model load progress 0.11"
Jun 06 19:12:14 ai001 ollama[590926]: time=2025-06-06T19:12:14.958Z level=DEBUG source=server.go:636 msg="model load progress 0.13"
Jun 06 19:12:15 ai001 ollama[590926]: time=2025-06-06T19:12:15.208Z level=DEBUG source=server.go:636 msg="model load progress 0.16"
Jun 06 19:12:15 ai001 ollama[590926]: time=2025-06-06T19:12:15.459Z level=DEBUG source=server.go:636 msg="model load progress 0.18"
Jun 06 19:12:15 ai001 ollama[590926]: time=2025-06-06T19:12:15.710Z level=DEBUG source=server.go:636 msg="model load progress 0.21"
Jun 06 19:12:15 ai001 ollama[590926]: time=2025-06-06T19:12:15.961Z level=DEBUG source=server.go:636 msg="model load progress 0.23"
Jun 06 19:12:16 ai001 ollama[590926]: time=2025-06-06T19:12:16.211Z level=DEBUG source=server.go:636 msg="model load progress 0.26"
Jun 06 19:12:16 ai001 ollama[590926]: time=2025-06-06T19:12:16.462Z level=DEBUG source=server.go:636 msg="model load progress 0.28"
Jun 06 19:12:16 ai001 ollama[590926]: time=2025-06-06T19:12:16.713Z level=DEBUG source=server.go:636 msg="model load progress 0.31"
Jun 06 19:12:16 ai001 ollama[590926]: time=2025-06-06T19:12:16.963Z level=DEBUG source=server.go:636 msg="model load progress 0.33"
Jun 06 19:12:17 ai001 ollama[590926]: time=2025-06-06T19:12:17.214Z level=DEBUG source=server.go:636 msg="model load progress 0.36"
Jun 06 19:12:17 ai001 ollama[590926]: time=2025-06-06T19:12:17.465Z level=DEBUG source=server.go:636 msg="model load progress 0.38"
Jun 06 19:12:17 ai001 ollama[590926]: time=2025-06-06T19:12:17.715Z level=DEBUG source=server.go:636 msg="model load progress 0.41"
Jun 06 19:12:17 ai001 ollama[590926]: time=2025-06-06T19:12:17.966Z level=DEBUG source=server.go:636 msg="model load progress 0.43"
Jun 06 19:12:18 ai001 ollama[590926]: time=2025-06-06T19:12:18.217Z level=DEBUG source=server.go:636 msg="model load progress 0.46"
Jun 06 19:12:18 ai001 ollama[590926]: time=2025-06-06T19:12:18.468Z level=DEBUG source=server.go:636 msg="model load progress 0.48"
Jun 06 19:12:18 ai001 ollama[590926]: time=2025-06-06T19:12:18.718Z level=DEBUG source=server.go:636 msg="model load progress 0.50"
Jun 06 19:12:18 ai001 ollama[590926]: time=2025-06-06T19:12:18.969Z level=DEBUG source=server.go:636 msg="model load progress 0.53"
Jun 06 19:12:19 ai001 ollama[590926]: time=2025-06-06T19:12:19.220Z level=DEBUG source=server.go:636 msg="model load progress 0.55"
Jun 06 19:12:19 ai001 ollama[590926]: time=2025-06-06T19:12:19.470Z level=DEBUG source=server.go:636 msg="model load progress 0.58"
Jun 06 19:12:19 ai001 ollama[590926]: time=2025-06-06T19:12:19.721Z level=DEBUG source=server.go:636 msg="model load progress 0.60"
Jun 06 19:12:19 ai001 ollama[590926]: time=2025-06-06T19:12:19.972Z level=DEBUG source=server.go:636 msg="model load progress 0.63"
Jun 06 19:12:20 ai001 ollama[590926]: time=2025-06-06T19:12:20.223Z level=DEBUG source=server.go:636 msg="model load progress 0.65"
Jun 06 19:12:20 ai001 ollama[590926]: time=2025-06-06T19:12:20.473Z level=DEBUG source=server.go:636 msg="model load progress 0.68"
Jun 06 19:12:20 ai001 ollama[590926]: time=2025-06-06T19:12:20.724Z level=DEBUG source=server.go:636 msg="model load progress 0.70"
Jun 06 19:12:20 ai001 ollama[590926]: time=2025-06-06T19:12:20.975Z level=DEBUG source=server.go:636 msg="model load progress 0.73"
Jun 06 19:12:21 ai001 ollama[590926]: time=2025-06-06T19:12:21.225Z level=DEBUG source=server.go:636 msg="model load progress 0.75"
Jun 06 19:12:21 ai001 ollama[590926]: time=2025-06-06T19:12:21.476Z level=DEBUG source=server.go:636 msg="model load progress 0.78"
Jun 06 19:12:21 ai001 ollama[590926]: time=2025-06-06T19:12:21.727Z level=DEBUG source=server.go:636 msg="model load progress 0.80"
Jun 06 19:12:21 ai001 ollama[590926]: time=2025-06-06T19:12:21.977Z level=DEBUG source=server.go:636 msg="model load progress 0.83"
Jun 06 19:12:22 ai001 ollama[590926]: time=2025-06-06T19:12:22.228Z level=DEBUG source=server.go:636 msg="model load progress 0.86"
Jun 06 19:12:22 ai001 ollama[590926]: time=2025-06-06T19:12:22.479Z level=DEBUG source=server.go:636 msg="model load progress 0.88"
Jun 06 19:12:22 ai001 ollama[590926]: time=2025-06-06T19:12:22.729Z level=DEBUG source=server.go:636 msg="model load progress 0.90"
Jun 06 19:12:22 ai001 ollama[590926]: time=2025-06-06T19:12:22.980Z level=DEBUG source=server.go:636 msg="model load progress 0.93"
Jun 06 19:12:23 ai001 ollama[590926]: time=2025-06-06T19:12:23.230Z level=DEBUG source=server.go:636 msg="model load progress 0.95"
Jun 06 19:12:23 ai001 ollama[590926]: time=2025-06-06T19:12:23.481Z level=DEBUG source=server.go:636 msg="model load progress 0.98"
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: constructing llama_context
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_seq_max = 2
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_ctx = 250000
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_ctx_per_seq = 125000
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_batch = 1024
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_ubatch = 512
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: causal_attn = 1
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: flash_attn = 0
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: freq_base = 1000000.0
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: freq_scale = 1
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_ctx_per_seq (125000) > n_ctx_train (40960) -- possible training context overflow
Jun 06 19:12:23 ai001 ollama[590926]: set_abort_callback: call
Jun 06 19:12:23 ai001 ollama[590926]: llama_context: CPU output buffer size = 1.20 MiB
Jun 06 19:12:23 ai001 ollama[590926]: create_memory: n_ctx = 250016 (padded)
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: kv_size = 250016, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1, padding = 32
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 0: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 1: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 2: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 3: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 4: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 5: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 6: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 7: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 8: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 9: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 10: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 11: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 12: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 13: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 14: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 15: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 16: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 17: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 18: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 19: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 20: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 21: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 22: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 23: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 24: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 25: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 26: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 27: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 28: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 29: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 30: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 31: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 32: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 33: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 34: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 35: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 36: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 37: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 38: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 39: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 40: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 41: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 42: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 43: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 44: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 45: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 46: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 47: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 48: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 49: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 50: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 51: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 52: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 53: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 54: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 55: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 56: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 57: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 58: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 59: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 60: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 61: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 62: dev = CPU
Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 63: dev = CPU

<!-- gh-comment-id:2950719695 --> @goactiongo commented on GitHub (Jun 6, 2025): Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: loading model tensors, this can take a while... (mmap = false) Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 0 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 1 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 2 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 3 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 4 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 5 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 6 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 7 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 8 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 9 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 10 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 11 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 12 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 13 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 14 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 15 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 16 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 17 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 18 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 19 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 20 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 21 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 22 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 23 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 24 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 25 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 26 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 27 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 28 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 29 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 30 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 31 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 32 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 33 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 34 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 35 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 36 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 37 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 38 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 39 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 40 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 41 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 42 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 43 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 44 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 45 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 46 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 47 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 48 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 49 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 50 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 51 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 52 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 53 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 54 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 55 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 56 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 57 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 58 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 59 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 60 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 61 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 62 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 63 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: layer 64 assigned to device CPU, is_swa = 0 Jun 06 19:12:13 ai001 ollama[590926]: load_tensors: CPU model buffer size = 19259.71 MiB Jun 06 19:12:13 ai001 ollama[590926]: load_all_data: no device found for buffer type CPU for async uploads Jun 06 19:12:13 ai001 ollama[590926]: time=2025-06-06T19:12:13.955Z level=DEBUG source=server.go:636 msg="model load progress 0.02" Jun 06 19:12:14 ai001 ollama[590926]: time=2025-06-06T19:12:14.205Z level=DEBUG source=server.go:636 msg="model load progress 0.06" Jun 06 19:12:14 ai001 ollama[590926]: time=2025-06-06T19:12:14.456Z level=DEBUG source=server.go:636 msg="model load progress 0.08" Jun 06 19:12:14 ai001 ollama[590926]: time=2025-06-06T19:12:14.707Z level=DEBUG source=server.go:636 msg="model load progress 0.11" Jun 06 19:12:14 ai001 ollama[590926]: time=2025-06-06T19:12:14.958Z level=DEBUG source=server.go:636 msg="model load progress 0.13" Jun 06 19:12:15 ai001 ollama[590926]: time=2025-06-06T19:12:15.208Z level=DEBUG source=server.go:636 msg="model load progress 0.16" Jun 06 19:12:15 ai001 ollama[590926]: time=2025-06-06T19:12:15.459Z level=DEBUG source=server.go:636 msg="model load progress 0.18" Jun 06 19:12:15 ai001 ollama[590926]: time=2025-06-06T19:12:15.710Z level=DEBUG source=server.go:636 msg="model load progress 0.21" Jun 06 19:12:15 ai001 ollama[590926]: time=2025-06-06T19:12:15.961Z level=DEBUG source=server.go:636 msg="model load progress 0.23" Jun 06 19:12:16 ai001 ollama[590926]: time=2025-06-06T19:12:16.211Z level=DEBUG source=server.go:636 msg="model load progress 0.26" Jun 06 19:12:16 ai001 ollama[590926]: time=2025-06-06T19:12:16.462Z level=DEBUG source=server.go:636 msg="model load progress 0.28" Jun 06 19:12:16 ai001 ollama[590926]: time=2025-06-06T19:12:16.713Z level=DEBUG source=server.go:636 msg="model load progress 0.31" Jun 06 19:12:16 ai001 ollama[590926]: time=2025-06-06T19:12:16.963Z level=DEBUG source=server.go:636 msg="model load progress 0.33" Jun 06 19:12:17 ai001 ollama[590926]: time=2025-06-06T19:12:17.214Z level=DEBUG source=server.go:636 msg="model load progress 0.36" Jun 06 19:12:17 ai001 ollama[590926]: time=2025-06-06T19:12:17.465Z level=DEBUG source=server.go:636 msg="model load progress 0.38" Jun 06 19:12:17 ai001 ollama[590926]: time=2025-06-06T19:12:17.715Z level=DEBUG source=server.go:636 msg="model load progress 0.41" Jun 06 19:12:17 ai001 ollama[590926]: time=2025-06-06T19:12:17.966Z level=DEBUG source=server.go:636 msg="model load progress 0.43" Jun 06 19:12:18 ai001 ollama[590926]: time=2025-06-06T19:12:18.217Z level=DEBUG source=server.go:636 msg="model load progress 0.46" Jun 06 19:12:18 ai001 ollama[590926]: time=2025-06-06T19:12:18.468Z level=DEBUG source=server.go:636 msg="model load progress 0.48" Jun 06 19:12:18 ai001 ollama[590926]: time=2025-06-06T19:12:18.718Z level=DEBUG source=server.go:636 msg="model load progress 0.50" Jun 06 19:12:18 ai001 ollama[590926]: time=2025-06-06T19:12:18.969Z level=DEBUG source=server.go:636 msg="model load progress 0.53" Jun 06 19:12:19 ai001 ollama[590926]: time=2025-06-06T19:12:19.220Z level=DEBUG source=server.go:636 msg="model load progress 0.55" Jun 06 19:12:19 ai001 ollama[590926]: time=2025-06-06T19:12:19.470Z level=DEBUG source=server.go:636 msg="model load progress 0.58" Jun 06 19:12:19 ai001 ollama[590926]: time=2025-06-06T19:12:19.721Z level=DEBUG source=server.go:636 msg="model load progress 0.60" Jun 06 19:12:19 ai001 ollama[590926]: time=2025-06-06T19:12:19.972Z level=DEBUG source=server.go:636 msg="model load progress 0.63" Jun 06 19:12:20 ai001 ollama[590926]: time=2025-06-06T19:12:20.223Z level=DEBUG source=server.go:636 msg="model load progress 0.65" Jun 06 19:12:20 ai001 ollama[590926]: time=2025-06-06T19:12:20.473Z level=DEBUG source=server.go:636 msg="model load progress 0.68" Jun 06 19:12:20 ai001 ollama[590926]: time=2025-06-06T19:12:20.724Z level=DEBUG source=server.go:636 msg="model load progress 0.70" Jun 06 19:12:20 ai001 ollama[590926]: time=2025-06-06T19:12:20.975Z level=DEBUG source=server.go:636 msg="model load progress 0.73" Jun 06 19:12:21 ai001 ollama[590926]: time=2025-06-06T19:12:21.225Z level=DEBUG source=server.go:636 msg="model load progress 0.75" Jun 06 19:12:21 ai001 ollama[590926]: time=2025-06-06T19:12:21.476Z level=DEBUG source=server.go:636 msg="model load progress 0.78" Jun 06 19:12:21 ai001 ollama[590926]: time=2025-06-06T19:12:21.727Z level=DEBUG source=server.go:636 msg="model load progress 0.80" Jun 06 19:12:21 ai001 ollama[590926]: time=2025-06-06T19:12:21.977Z level=DEBUG source=server.go:636 msg="model load progress 0.83" Jun 06 19:12:22 ai001 ollama[590926]: time=2025-06-06T19:12:22.228Z level=DEBUG source=server.go:636 msg="model load progress 0.86" Jun 06 19:12:22 ai001 ollama[590926]: time=2025-06-06T19:12:22.479Z level=DEBUG source=server.go:636 msg="model load progress 0.88" Jun 06 19:12:22 ai001 ollama[590926]: time=2025-06-06T19:12:22.729Z level=DEBUG source=server.go:636 msg="model load progress 0.90" Jun 06 19:12:22 ai001 ollama[590926]: time=2025-06-06T19:12:22.980Z level=DEBUG source=server.go:636 msg="model load progress 0.93" Jun 06 19:12:23 ai001 ollama[590926]: time=2025-06-06T19:12:23.230Z level=DEBUG source=server.go:636 msg="model load progress 0.95" Jun 06 19:12:23 ai001 ollama[590926]: time=2025-06-06T19:12:23.481Z level=DEBUG source=server.go:636 msg="model load progress 0.98" Jun 06 19:12:23 ai001 ollama[590926]: llama_context: constructing llama_context Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_seq_max = 2 Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_ctx = 250000 Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_ctx_per_seq = 125000 Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_batch = 1024 Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_ubatch = 512 Jun 06 19:12:23 ai001 ollama[590926]: llama_context: causal_attn = 1 Jun 06 19:12:23 ai001 ollama[590926]: llama_context: flash_attn = 0 Jun 06 19:12:23 ai001 ollama[590926]: llama_context: freq_base = 1000000.0 Jun 06 19:12:23 ai001 ollama[590926]: llama_context: freq_scale = 1 Jun 06 19:12:23 ai001 ollama[590926]: llama_context: n_ctx_per_seq (125000) > n_ctx_train (40960) -- possible training context overflow Jun 06 19:12:23 ai001 ollama[590926]: set_abort_callback: call Jun 06 19:12:23 ai001 ollama[590926]: llama_context: CPU output buffer size = 1.20 MiB Jun 06 19:12:23 ai001 ollama[590926]: create_memory: n_ctx = 250016 (padded) Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: kv_size = 250016, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1, padding = 32 Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 0: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 1: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 2: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 3: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 4: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 5: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 6: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 7: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 8: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 9: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 10: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 11: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 12: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 13: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 14: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 15: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 16: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 17: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 18: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 19: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 20: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 21: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 22: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 23: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 24: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 25: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 26: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 27: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 28: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 29: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 30: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 31: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 32: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 33: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 34: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 35: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 36: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 37: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 38: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 39: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 40: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 41: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 42: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 43: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 44: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 45: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 46: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 47: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 48: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 49: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 50: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 51: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 52: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 53: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 54: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 55: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 56: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 57: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 58: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 59: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 60: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 61: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 62: dev = CPU Jun 06 19:12:23 ai001 ollama[590926]: llama_kv_cache_unified: layer 63: dev = CPU
GiteaMirror commented 2026-04-12 19:17:59 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 6, 2025):

So what's the question? Why is the model running on the CPU? The context is too large to fit on a GPU.

<!-- gh-comment-id:2950723924 --> @rick-github commented on GitHub (Jun 6, 2025): So what's the question? Why is the model running on the CPU? The context is too large to fit on a GPU.
GiteaMirror commented 2026-04-12 19:18:00 -05:00
Author
Owner
Copy Link

@goactiongo commented on GitHub (Jun 6, 2025):

Got it .Thanks

<!-- gh-comment-id:2950726477 --> @goactiongo commented on GitHub (Jun 6, 2025): Got it .Thanks
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#7253
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?