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 #9915] nvidia/Llama-3_3-Nemotron-Super-49B-v1 #32252

New Issue
Closed
opened 2026-04-22 13:20:35 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-22 13:20:35 -05:00
Owner
Copy Link

Originally created by @dpk-it on GitHub (Mar 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9915

https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1

Originally created by @dpk-it on GitHub (Mar 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9915 https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1
GiteaMirror added the model label 2026-04-22 13:20:35 -05:00
GiteaMirror commented 2026-04-22 13:20:38 -05:00
Author
Owner
Copy Link

@mmb78 commented on GitHub (Mar 20, 2025):

just tried this (does not work):

ollama run hf.co/bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF:Q4_K_M
Error: Post "http://127.0.0.1:11434/api/generate": EOF

ollama show hf.co/bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF:Q4_K_M
Model
architecture deci
parameters 49.9B
context length 131072
embedding length 8192
quantization unknown

Parameters
stop "<|im_start|>"
stop "<|im_end|>"

<!-- gh-comment-id:2741549329 --> @mmb78 commented on GitHub (Mar 20, 2025): just tried this (does not work): ollama run hf.co/bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF:Q4_K_M Error: Post "http://127.0.0.1:11434/api/generate": EOF ollama show hf.co/bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF:Q4_K_M Model architecture deci parameters 49.9B context length 131072 embedding length 8192 quantization unknown Parameters stop "<|im_start|>" stop "<|im_end|>"
GiteaMirror commented 2026-04-22 13:20:39 -05:00
Author
Owner
Copy Link

@dpk-it commented on GitHub (Mar 20, 2025):

@mmb78 I tried several quantization options, it crashes ollama on my system during model initialization https://github.com/ollama/ollama/issues/9911 .. other models work fine

<!-- gh-comment-id:2741587837 --> @dpk-it commented on GitHub (Mar 20, 2025): @mmb78 I tried several quantization options, it crashes ollama on my system during model initialization https://github.com/ollama/ollama/issues/9911 .. other models work fine
GiteaMirror commented 2026-04-22 13:20:40 -05:00
Author
Owner
Copy Link

@nickheyer commented on GitHub (Mar 21, 2025):

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

<!-- gh-comment-id:2741957953 --> @nickheyer commented on GitHub (Mar 21, 2025): interface conversion: interface {} is *ggml.array, not uint32
GiteaMirror commented 2026-04-22 13:20:42 -05:00
Author
Owner
Copy Link

@charliboy commented on GitHub (Mar 21, 2025):

Ollmama 0.6.0 version has the same issue，

<!-- gh-comment-id:2742539270 --> @charliboy commented on GitHub (Mar 21, 2025): Ollmama 0.6.0 version has the same issue，
GiteaMirror commented 2026-04-22 13:20:43 -05:00
Author
Owner
Copy Link

@Tanote650 commented on GitHub (Mar 21, 2025):

Already 2 months ago an Ollama update for the Nemotron models was worked out and made available, see post #8460. Why this has not yet been considered in one of the updates of Ollama I can not say.

<!-- gh-comment-id:2743003613 --> @Tanote650 commented on GitHub (Mar 21, 2025): Already 2 months ago an Ollama update for the Nemotron models was worked out and made available, see post #8460. Why this has not yet been considered in one of the updates of Ollama I can not say.
GiteaMirror commented 2026-04-22 13:20:43 -05:00
Author
Owner
Copy Link

@JeroenAdam commented on GitHub (Mar 21, 2025):

I tried this and Ollmama v0.6.2 crashes, although works fine with llama.cpp b4856 from two weeks ago.

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:2743838664 --> @JeroenAdam commented on GitHub (Mar 21, 2025): I tried this and Ollmama v0.6.2 crashes, although works fine with llama.cpp b4856 from two weeks ago. 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
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#32252
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?