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 #8460] Llama-3_1-Nemotron-51B-Instruct #67497

New Issue
Closed
opened 2026-05-04 10:33:06 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-05-04 10:33:06 -05:00
Owner
Copy Link

Originally created by @Tanote650 on GitHub (Jan 16, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8460

Please add the Nvidia Model.

https://huggingface.co/bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF

Originally created by @Tanote650 on GitHub (Jan 16, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8460 Please add the Nvidia Model. https://huggingface.co/bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF
GiteaMirror added the model label 2026-05-04 10:33:06 -05:00
GiteaMirror commented 2026-05-04 10:33:08 -05:00
Author
Owner
Copy Link

@Tanote650 commented on GitHub (Jan 25, 2025):

Thank you very much

<!-- gh-comment-id:2613856271 --> @Tanote650 commented on GitHub (Jan 25, 2025): Thank you very much
GiteaMirror commented 2026-05-04 10:33:08 -05:00
Author
Owner
Copy Link

@dpk-it commented on GitHub (Mar 21, 2025):

Tested 'hf.co/bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF:Q4_K_L' and 'hf.co/bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF:Q4_K_M', does not work in version 0.6.2 as stated in panic: interface conversion: interface {} is *ggml.array, not uint32 #9911

2025/03/21 19:25:27 routes.go:1230: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE:q8_0 OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-03-21T19:25:27.235Z level=INFO source=images.go:432 msg="total blobs: 179"
time=2025-03-21T19:25:27.238Z level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-03-21T19:25:27.239Z level=INFO source=routes.go:1297 msg="Listening on [::]:11434 (version 0.6.2)"
time=2025-03-21T19:25:27.240Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-03-21T19:25:28.071Z level=INFO source=types.go:130 msg="inference compute" id=GPU-e8a01a94-7d0f-f68d-f1b9-6d652b29b486 library=cuda variant=v12 compute=12.0 driver=12.8 name="NVIDIA GeForce RTX 5090" total="31.8 GiB" available="30.1 GiB"
time=2025-03-21T19:25:28.071Z level=INFO source=types.go:130 msg="inference compute" id=GPU-f5e9aa1d-8aae-882d-3c1a-8439274b917e library=cuda variant=v12 compute=8.9 driver=12.8 name="NVIDIA GeForce RTX 4070 Ti SUPER" total="16.0 GiB" available="14.7 GiB"
time=2025-03-21T19:25:28.071Z level=INFO source=types.go:130 msg="inference compute" id=GPU-a3276781-03b0-19e3-9aff-f476adf829ef library=cuda variant=v12 compute=8.9 driver=12.8 name="NVIDIA GeForce RTX 4060 Ti" total="16.0 GiB" available="14.9 GiB"
time=2025-03-21T19:25:42.566Z level=WARN source=ggml.go:149 msg="key not found" key=deci.vision.block_count default=0
panic: interface conversion: interface {} is *ggml.array, not uint32

goroutine 82 [running]:
github.com/ollama/ollama/fs/ggml.keyValue[...](0xc0003c7e60, {0x556f679e0d4d, 0x14}, {0xc0003b02b0, 0x1, 0x0})
        github.com/ollama/ollama/fs/ggml/ggml.go:146 +0x2de
github.com/ollama/ollama/fs/ggml.KV.Uint(...)
        github.com/ollama/ollama/fs/ggml/ggml.go:96
github.com/ollama/ollama/fs/ggml.KV.HeadCount(...)
        github.com/ollama/ollama/fs/ggml/ggml.go:56
github.com/ollama/ollama/fs/ggml.KV.EmbeddingHeadCount(0xc0003c7e60)
        github.com/ollama/ollama/fs/ggml/ggml.go:64 +0x5e
github.com/ollama/ollama/fs/ggml.KV.EmbeddingHeadCountK(0xc0003c7e60)
        github.com/ollama/ollama/fs/ggml/ggml.go:72 +0x18
github.com/ollama/ollama/fs/ggml.GGML.SupportsFlashAttention({{0x556f67e540e8?, 0xc0005b74a0?}, {0x556f67e54098?, 0xc0004e9008?}})
        github.com/ollama/ollama/fs/ggml/ggml.go:648 +0x159
github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...})
        github.com/ollama/ollama/llm/memory.go:133 +0x568
github.com/ollama/ollama/llm.PredictServerFit({0xc000399ba8?, 0x556f66ba0de5?, 0xc0003998c0?}, 0xc0002b2ee0, {0xc000399918?, _, _}, {0x0, 0x0, 0x0}, ...)
        github.com/ollama/ollama/llm/memory.go:23 +0xbd
github.com/ollama/ollama/server.pickBestFullFitByLibrary(0xc0006d64b0, 0xc0002b2ee0, {0xc0002b7808?, 0x3?, 0x4?}, 0xc0003a3cf8)
        github.com/ollama/ollama/server/sched.go:714 +0x6f3
github.com/ollama/ollama/server.(*Scheduler).processPending(0xc000590180, {0x556f67e58020, 0xc0001299a0})
        github.com/ollama/ollama/server/sched.go:226 +0xe6b
github.com/ollama/ollama/server.(*Scheduler).Run.func1()
        github.com/ollama/ollama/server/sched.go:108 +0x1f
created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1
        github.com/ollama/ollama/server/sched.go:107 +0xb1
<!-- gh-comment-id:2744270756 --> @dpk-it commented on GitHub (Mar 21, 2025): Tested 'hf.co/bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF:Q4_K_L' and 'hf.co/bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF:Q4_K_M', does not work in version 0.6.2 as stated in [panic: interface conversion: interface {} is *ggml.array, not uint32 #9911](https://github.com/ollama/ollama/issues/9911) ``` 2025/03/21 19:25:27 routes.go:1230: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE:q8_0 OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-03-21T19:25:27.235Z level=INFO source=images.go:432 msg="total blobs: 179" time=2025-03-21T19:25:27.238Z level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-03-21T19:25:27.239Z level=INFO source=routes.go:1297 msg="Listening on [::]:11434 (version 0.6.2)" time=2025-03-21T19:25:27.240Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-03-21T19:25:28.071Z level=INFO source=types.go:130 msg="inference compute" id=GPU-e8a01a94-7d0f-f68d-f1b9-6d652b29b486 library=cuda variant=v12 compute=12.0 driver=12.8 name="NVIDIA GeForce RTX 5090" total="31.8 GiB" available="30.1 GiB" time=2025-03-21T19:25:28.071Z level=INFO source=types.go:130 msg="inference compute" id=GPU-f5e9aa1d-8aae-882d-3c1a-8439274b917e library=cuda variant=v12 compute=8.9 driver=12.8 name="NVIDIA GeForce RTX 4070 Ti SUPER" total="16.0 GiB" available="14.7 GiB" time=2025-03-21T19:25:28.071Z level=INFO source=types.go:130 msg="inference compute" id=GPU-a3276781-03b0-19e3-9aff-f476adf829ef library=cuda variant=v12 compute=8.9 driver=12.8 name="NVIDIA GeForce RTX 4060 Ti" total="16.0 GiB" available="14.9 GiB" time=2025-03-21T19:25:42.566Z level=WARN source=ggml.go:149 msg="key not found" key=deci.vision.block_count default=0 panic: interface conversion: interface {} is *ggml.array, not uint32 goroutine 82 [running]: github.com/ollama/ollama/fs/ggml.keyValue[...](0xc0003c7e60, {0x556f679e0d4d, 0x14}, {0xc0003b02b0, 0x1, 0x0}) github.com/ollama/ollama/fs/ggml/ggml.go:146 +0x2de github.com/ollama/ollama/fs/ggml.KV.Uint(...) github.com/ollama/ollama/fs/ggml/ggml.go:96 github.com/ollama/ollama/fs/ggml.KV.HeadCount(...) github.com/ollama/ollama/fs/ggml/ggml.go:56 github.com/ollama/ollama/fs/ggml.KV.EmbeddingHeadCount(0xc0003c7e60) github.com/ollama/ollama/fs/ggml/ggml.go:64 +0x5e github.com/ollama/ollama/fs/ggml.KV.EmbeddingHeadCountK(0xc0003c7e60) github.com/ollama/ollama/fs/ggml/ggml.go:72 +0x18 github.com/ollama/ollama/fs/ggml.GGML.SupportsFlashAttention({{0x556f67e540e8?, 0xc0005b74a0?}, {0x556f67e54098?, 0xc0004e9008?}}) github.com/ollama/ollama/fs/ggml/ggml.go:648 +0x159 github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...}) github.com/ollama/ollama/llm/memory.go:133 +0x568 github.com/ollama/ollama/llm.PredictServerFit({0xc000399ba8?, 0x556f66ba0de5?, 0xc0003998c0?}, 0xc0002b2ee0, {0xc000399918?, _, _}, {0x0, 0x0, 0x0}, ...) github.com/ollama/ollama/llm/memory.go:23 +0xbd github.com/ollama/ollama/server.pickBestFullFitByLibrary(0xc0006d64b0, 0xc0002b2ee0, {0xc0002b7808?, 0x3?, 0x4?}, 0xc0003a3cf8) github.com/ollama/ollama/server/sched.go:714 +0x6f3 github.com/ollama/ollama/server.(*Scheduler).processPending(0xc000590180, {0x556f67e58020, 0xc0001299a0}) github.com/ollama/ollama/server/sched.go:226 +0xe6b github.com/ollama/ollama/server.(*Scheduler).Run.func1() github.com/ollama/ollama/server/sched.go:108 +0x1f created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1 github.com/ollama/ollama/server/sched.go:107 +0xb1 ```
GiteaMirror commented 2026-05-04 10:33:09 -05:00
Author
Owner
Copy Link

@JeroenAdam commented on GitHub (Mar 23, 2025):

Same issue with the newer Nemotron: https://ollama.com/MHKetbi/nvidia_Llama-3.3-Nemotron-Super-49B-v1

panic: interface conversion: interface {} is *ggml.array, not uint32

goroutine 16 [running]:
github.com/ollama/ollama/fs/ggml.keyValue[...](0xc0002f2ff0, {0x55e8beea7d4d, 0x14}, {0xc0005d6b98, 0x1, 0x0})
github.com/ollama/ollama/fs/ggml/ggml.go:146 +0x2de
github.com/ollama/ollama/fs/ggml.KV.Uint(...)
github.com/ollama/ollama/fs/ggml/ggml.go:96
github.com/ollama/ollama/fs/ggml.KV.HeadCount(...)
github.com/ollama/ollama/fs/ggml/ggml.go:56
github.com/ollama/ollama/fs/ggml.KV.EmbeddingHeadCount(0xc0002f2ff0)
github.com/ollama/ollama/fs/ggml/ggml.go:64 +0x5e
github.com/ollama/ollama/fs/ggml.KV.EmbeddingHeadCountK(0xc0002f2ff0)
github.com/ollama/ollama/fs/ggml/ggml.go:72 +0x18
github.com/ollama/ollama/fs/ggml.GGML.SupportsFlashAttention({{0x55e8bf31b0e8?, 0xc0006f0f50?}, {0x55e8bf31b098?, 0xc000489008?}})
github.com/ollama/ollama/fs/ggml/ggml.go:648 +0x159
github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, , {, _, _}, {{0x20000, 0x200, 0xffffffffffffffff, ...}, ...})
github.com/ollama/ollama/llm/memory.go:133 +0x568
github.com/ollama/ollama/llm.PredictServerFit({0xc000785ba8?, 0x55e8be067de5?, 0xc0007858c0?}, 0xc00015a020, {0xc000785918?, _, _}, {0x0, 0x0, 0x0}, ...)
github.com/ollama/ollama/llm/memory.go:23 +0xbd
github.com/ollama/ollama/server.pickBestFullFitByLibrary(0xc00004c0f0, 0xc00015a020, {0xc0001d0240?, 0x1?, 0x1?}, 0xc000045cf8)
github.com/ollama/ollama/server/sched.go:714 +0x6f3
github.com/ollama/ollama/server.(*Scheduler).processPending(0xc0001a91a0, {0x55e8bf31f020, 0xc0003b2550})
github.com/ollama/ollama/server/sched.go:226 +0xe6b
github.com/ollama/ollama/server.(*Scheduler).Run.func1()
github.com/ollama/ollama/server/sched.go:108 +0x1f
created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1
github.com/ollama/ollama/server/sched.go:107 +0xb1

<!-- gh-comment-id:2746030556 --> @JeroenAdam commented on GitHub (Mar 23, 2025): Same issue with the newer Nemotron: https://ollama.com/MHKetbi/nvidia_Llama-3.3-Nemotron-Super-49B-v1 panic: interface conversion: interface {} is *ggml.array, not uint32 goroutine 16 [running]: github.com/ollama/ollama/fs/ggml.keyValue[...](0xc0002f2ff0, {0x55e8beea7d4d, 0x14}, {0xc0005d6b98, 0x1, 0x0}) github.com/ollama/ollama/fs/ggml/ggml.go:146 +0x2de github.com/ollama/ollama/fs/ggml.KV.Uint(...) github.com/ollama/ollama/fs/ggml/ggml.go:96 github.com/ollama/ollama/fs/ggml.KV.HeadCount(...) github.com/ollama/ollama/fs/ggml/ggml.go:56 github.com/ollama/ollama/fs/ggml.KV.EmbeddingHeadCount(0xc0002f2ff0) github.com/ollama/ollama/fs/ggml/ggml.go:64 +0x5e github.com/ollama/ollama/fs/ggml.KV.EmbeddingHeadCountK(0xc0002f2ff0) github.com/ollama/ollama/fs/ggml/ggml.go:72 +0x18 github.com/ollama/ollama/fs/ggml.GGML.SupportsFlashAttention({{0x55e8bf31b0e8?, 0xc0006f0f50?}, {0x55e8bf31b098?, 0xc000489008?}}) github.com/ollama/ollama/fs/ggml/ggml.go:648 +0x159 github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x20000, 0x200, 0xffffffffffffffff, ...}, ...}) github.com/ollama/ollama/llm/memory.go:133 +0x568 github.com/ollama/ollama/llm.PredictServerFit({0xc000785ba8?, 0x55e8be067de5?, 0xc0007858c0?}, 0xc00015a020, {0xc000785918?, _, _}, {0x0, 0x0, 0x0}, ...) github.com/ollama/ollama/llm/memory.go:23 +0xbd github.com/ollama/ollama/server.pickBestFullFitByLibrary(0xc00004c0f0, 0xc00015a020, {0xc0001d0240?, 0x1?, 0x1?}, 0xc000045cf8) github.com/ollama/ollama/server/sched.go:714 +0x6f3 github.com/ollama/ollama/server.(*Scheduler).processPending(0xc0001a91a0, {0x55e8bf31f020, 0xc0003b2550}) github.com/ollama/ollama/server/sched.go:226 +0xe6b github.com/ollama/ollama/server.(*Scheduler).Run.func1() github.com/ollama/ollama/server/sched.go:108 +0x1f created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1 github.com/ollama/ollama/server/sched.go:107 +0xb1
GiteaMirror commented 2026-05-04 10:33:10 -05:00
Author
Owner
Copy Link

@yt-koike commented on GitHub (Jul 8, 2025):

Same issue with https://huggingface.co/yt-koike/plamo-2-1b-gguf as well.

ollama  | [GIN] 2025/07/08 - 08:28:29 | 200 |      47.649µs |       127.0.0.1 | HEAD     "/"
ollama  | time=2025-07-08T08:28:29.309Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama  | time=2025-07-08T08:28:29.320Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama  | [GIN] 2025/07/08 - 08:28:29 | 200 |   24.060833ms |       127.0.0.1 | POST     "/api/show"
ollama  | time=2025-07-08T08:28:29.334Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama  | time=2025-07-08T08:28:29.509Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama  | time=2025-07-08T08:28:29.526Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama  | time=2025-07-08T08:28:29.526Z level=WARN source=ggml.go:152 msg="key not found" key=plamo2.vision.block_count default=0
ollama  | panic: interface conversion: interface {} is *ggml.array[int32], not uint32
ollama  |
ollama  | goroutine 52 [running]:
ollama  | github.com/ollama/ollama/fs/ggml.keyValue[...](0xc000565b30, {0x5836071a4ced, 0x17}, {0xc000439a30, 0x2, 0x0})
ollama  |       github.com/ollama/ollama/fs/ggml/ggml.go:149 +0x2de
ollama  | github.com/ollama/ollama/fs/ggml.KV.Uint(...)
ollama  |       github.com/ollama/ollama/fs/ggml/ggml.go:96
ollama  | github.com/ollama/ollama/fs/ggml.KV.HeadCountKV(...)
ollama  |       github.com/ollama/ollama/fs/ggml/ggml.go:60
ollama  | github.com/ollama/ollama/fs/ggml.GGML.GraphSize({{0x583607628b68?, 0xc00052c730?}, {0x583607628b18?, 0xc00018d808?}}, 0x2000, 0x200, 0x2, {0x0, 0x0})
ollama  |       github.com/ollama/ollama/fs/ggml/ggml.go:417 +0x1b8
ollama  | github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...}, ...)
ollama  |       github.com/ollama/ollama/llm/memory.go:140 +0x665
ollama  | github.com/ollama/ollama/llm.PredictServerFit({0xc000305b88?, 0x0?, 0x0?}, 0xc000482100, {0x58360667e8ed?, _, _}, {0x0, 0x0, 0x0}, ...)
ollama  |       github.com/ollama/ollama/llm/memory.go:23 +0xe5
ollama  | github.com/ollama/ollama/server.pickBestFullFitByLibrary(0xc0004b00f0, 0xc000482100, {0xc0000d8240?, 0x1?, 0x1?}, 0xc0004adcd8)
ollama  |       github.com/ollama/ollama/server/sched.go:753 +0x6fb
ollama  | github.com/ollama/ollama/server.(*Scheduler).processPending(0xc000111380, {0x58360762cb20, 0xc0006a71d0})
ollama  |       github.com/ollama/ollama/server/sched.go:228 +0xf0b
ollama  | github.com/ollama/ollama/server.(*Scheduler).Run.func1()
ollama  |       github.com/ollama/ollama/server/sched.go:109 +0x1f
ollama  | created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1
ollama  |       github.com/ollama/ollama/server/sched.go:108 +0xb1
ollama  | 2025/07/08 08:28:29 routes.go:1233: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
ollama  | time=2025-07-08T08:28:29.970Z level=INFO source=images.go:463 msg="total blobs: 68"
ollama  | time=2025-07-08T08:28:29.971Z level=INFO source=images.go:470 msg="total unused blobs removed: 0"
ollama  | time=2025-07-08T08:28:29.972Z level=INFO source=routes.go:1300 msg="Listening on [::]:11434 (version 0.6.8)"
ollama  | time=2025-07-08T08:28:29.972Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
ollama  | time=2025-07-08T08:28:30.140Z level=INFO source=types.go:130 msg="inference compute" id=GPU-743bd432-c954-e10f-b04d-db1b4f5ed5ea library=cuda variant=v12 compute=8.9 driver=12.7 name="NVIDIA GeForce RTX 4070 Ti SUPER" total="15.6 GiB" available="9.4 GiB"
<!-- gh-comment-id:3047891279 --> @yt-koike commented on GitHub (Jul 8, 2025): Same issue with https://huggingface.co/yt-koike/plamo-2-1b-gguf as well. ``` ollama | [GIN] 2025/07/08 - 08:28:29 | 200 | 47.649µs | 127.0.0.1 | HEAD "/" ollama | time=2025-07-08T08:28:29.309Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | time=2025-07-08T08:28:29.320Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | [GIN] 2025/07/08 - 08:28:29 | 200 | 24.060833ms | 127.0.0.1 | POST "/api/show" ollama | time=2025-07-08T08:28:29.334Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | time=2025-07-08T08:28:29.509Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | time=2025-07-08T08:28:29.526Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | time=2025-07-08T08:28:29.526Z level=WARN source=ggml.go:152 msg="key not found" key=plamo2.vision.block_count default=0 ollama | panic: interface conversion: interface {} is *ggml.array[int32], not uint32 ollama | ollama | goroutine 52 [running]: ollama | github.com/ollama/ollama/fs/ggml.keyValue[...](0xc000565b30, {0x5836071a4ced, 0x17}, {0xc000439a30, 0x2, 0x0}) ollama | github.com/ollama/ollama/fs/ggml/ggml.go:149 +0x2de ollama | github.com/ollama/ollama/fs/ggml.KV.Uint(...) ollama | github.com/ollama/ollama/fs/ggml/ggml.go:96 ollama | github.com/ollama/ollama/fs/ggml.KV.HeadCountKV(...) ollama | github.com/ollama/ollama/fs/ggml/ggml.go:60 ollama | github.com/ollama/ollama/fs/ggml.GGML.GraphSize({{0x583607628b68?, 0xc00052c730?}, {0x583607628b18?, 0xc00018d808?}}, 0x2000, 0x200, 0x2, {0x0, 0x0}) ollama | github.com/ollama/ollama/fs/ggml/ggml.go:417 +0x1b8 ollama | github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...}, ...) ollama | github.com/ollama/ollama/llm/memory.go:140 +0x665 ollama | github.com/ollama/ollama/llm.PredictServerFit({0xc000305b88?, 0x0?, 0x0?}, 0xc000482100, {0x58360667e8ed?, _, _}, {0x0, 0x0, 0x0}, ...) ollama | github.com/ollama/ollama/llm/memory.go:23 +0xe5 ollama | github.com/ollama/ollama/server.pickBestFullFitByLibrary(0xc0004b00f0, 0xc000482100, {0xc0000d8240?, 0x1?, 0x1?}, 0xc0004adcd8) ollama | github.com/ollama/ollama/server/sched.go:753 +0x6fb ollama | github.com/ollama/ollama/server.(*Scheduler).processPending(0xc000111380, {0x58360762cb20, 0xc0006a71d0}) ollama | github.com/ollama/ollama/server/sched.go:228 +0xf0b ollama | github.com/ollama/ollama/server.(*Scheduler).Run.func1() ollama | github.com/ollama/ollama/server/sched.go:109 +0x1f ollama | created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1 ollama | github.com/ollama/ollama/server/sched.go:108 +0xb1 ollama | 2025/07/08 08:28:29 routes.go:1233: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" ollama | time=2025-07-08T08:28:29.970Z level=INFO source=images.go:463 msg="total blobs: 68" ollama | time=2025-07-08T08:28:29.971Z level=INFO source=images.go:470 msg="total unused blobs removed: 0" ollama | time=2025-07-08T08:28:29.972Z level=INFO source=routes.go:1300 msg="Listening on [::]:11434 (version 0.6.8)" ollama | time=2025-07-08T08:28:29.972Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" ollama | time=2025-07-08T08:28:30.140Z level=INFO source=types.go:130 msg="inference compute" id=GPU-743bd432-c954-e10f-b04d-db1b4f5ed5ea library=cuda variant=v12 compute=8.9 driver=12.7 name="NVIDIA GeForce RTX 4070 Ti SUPER" total="15.6 GiB" available="9.4 GiB" ```
GiteaMirror commented 2026-05-04 10:33:10 -05:00
Author
Owner
Copy Link

@yt-koike commented on GitHub (Jul 8, 2025):

Never mind. After upgrading my ollama to 0.9.5, it says error loading model: error loading model architecture: unknown model architecture: 'plamo2'. This could be fixed with https://github.com/ggml-org/llama.cpp/pull/14560.

<!-- gh-comment-id:3048096894 --> @yt-koike commented on GitHub (Jul 8, 2025): Never mind. After upgrading my ollama to 0.9.5, it says `error loading model: error loading model architecture: unknown model architecture: 'plamo2'`. This could be fixed with https://github.com/ggml-org/llama.cpp/pull/14560.
GiteaMirror commented 2026-05-04 10:33:11 -05:00
Author
Owner
Copy Link

@mitmul commented on GitHub (Oct 24, 2025):

@yt-koike While I understand this is essentially about different error issues, I'll mention it anyway: if you're trying to run a plamo2 model in Ollama, applying just this one line of changes from this PR: https://github.com/ollama/ollama/pull/12761 might make it work.

<!-- gh-comment-id:3443036919 --> @mitmul commented on GitHub (Oct 24, 2025): @yt-koike While I understand this is essentially about different error issues, I'll mention it anyway: if you're trying to run a plamo2 model in Ollama, applying just this one line of changes from this PR: https://github.com/ollama/ollama/pull/12761 might make it work.
GiteaMirror commented 2026-05-04 10:33:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 5, 2026):

$ ollama -v
ollama version is 0.13.5

$ ollama run hf.co/bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF:Q4_K_M hello
pulling manifest 
pulling fd11e8991106: 100% ▕██████████████████▏  31 GB                         
pulling 948af2743fc7: 100% ▕██████████████████▏ 1.5 KB                         
pulling 6c0b08d96525: 100% ▕██████████████████▏   65 B                         
pulling f9f3562e8a50: 100% ▕██████████████████▏  547 B                         
verifying sha256 digest 
writing manifest 
success 
Hello! How can I help you today?
<!-- gh-comment-id:3709262881 --> @rick-github commented on GitHub (Jan 5, 2026): ```console $ ollama -v ollama version is 0.13.5 $ ollama run hf.co/bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF:Q4_K_M hello pulling manifest pulling fd11e8991106: 100% ▕██████████████████▏ 31 GB pulling 948af2743fc7: 100% ▕██████████████████▏ 1.5 KB pulling 6c0b08d96525: 100% ▕██████████████████▏ 65 B pulling f9f3562e8a50: 100% ▕██████████████████▏ 547 B verifying sha256 digest writing manifest success Hello! How can I help you today? ```
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 model
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#67497
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?