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 #11433] Support EXAONE-4.0 #7547

New Issue
Closed
opened 2026-04-12 19:38:48 -05:00 by GiteaMirror · 10 comments
GiteaMirror commented 2026-04-12 19:38:48 -05:00
Owner
Copy Link

Originally created by @y1xia0w on GitHub (Jul 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11433

Could you Ollama team kindly consider supporting the latest EXAONE 4.0 models released on Huggingface? Thank you!

We introduce EXAONE 4.0, which integrates a Non-reasoning mode and Reasoning mode to achieve both the excellent usability of EXAONE 3.5 and the advanced reasoning abilities of EXAONE Deep. To pave the way for the agentic AI era, EXAONE 4.0 incorporates essential features such as agentic tool use, and its multilingual capabilities are extended to support Spanish in addition to English and Korean.

The EXAONE 4.0 model series consists of two sizes: a mid-size 32B model optimized for high performance, and a small-size 1.2B model designed for on-device applications.

They have uploaded GGUF format:
EXAONE-4.0-1.2B-GGUF
EXAONE-4.0-32B-GGUF

Originally created by @y1xia0w on GitHub (Jul 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11433 Could you Ollama team kindly consider supporting the latest [EXAONE 4.0](https://huggingface.co/collections/LGAI-EXAONE/exaone-40-686b2e0069800c835ed48375) models released on Huggingface? Thank you! > We introduce EXAONE 4.0, which integrates a Non-reasoning mode and Reasoning mode to achieve both the excellent usability of [EXAONE 3.5](https://github.com/LG-AI-EXAONE/EXAONE-3.5) and the advanced reasoning abilities of [EXAONE Deep](https://github.com/LG-AI-EXAONE/EXAONE-Deep). To pave the way for the agentic AI era, EXAONE 4.0 incorporates essential features such as agentic tool use, and its multilingual capabilities are extended to support Spanish in addition to English and Korean. > > The EXAONE 4.0 model series consists of two sizes: a mid-size 32B model optimized for high performance, and a small-size 1.2B model designed for on-device applications. They have uploaded GGUF format: [EXAONE-4.0-1.2B-GGUF](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF) [EXAONE-4.0-32B-GGUF](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B-GGUF)
GiteaMirror added the model label 2026-04-12 19:38:48 -05:00
GiteaMirror commented 2026-04-12 19:38:49 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 15, 2025):

https://github.com/ggml-org/llama.cpp/pull/14630

<!-- gh-comment-id:3075648879 --> @rick-github commented on GitHub (Jul 15, 2025): https://github.com/ggml-org/llama.cpp/pull/14630
GiteaMirror commented 2026-04-12 19:38:49 -05:00
Author
Owner
Copy Link

@blakkd commented on GitHub (Jul 16, 2025):

That sounds promising! Applying their PR + change proposed there did the trick for me it! I don't have any problem and am using it right now.

But I know, let's wait it for the last approvals ;)

<!-- gh-comment-id:3078101568 --> @blakkd commented on GitHub (Jul 16, 2025): That sounds promising! Applying their PR + change proposed [there](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B/discussions/2) did the trick for me it! I don't have any problem and am using it right now. But I know, let's wait it for the last approvals ;)
GiteaMirror commented 2026-04-12 19:38:50 -05:00
Author
Owner
Copy Link

@zimdin12 commented on GitHub (Jul 18, 2025):

Keeping my eye on this :)

<!-- gh-comment-id:3090037301 --> @zimdin12 commented on GitHub (Jul 18, 2025): Keeping my eye on this :)
GiteaMirror commented 2026-04-12 19:38:51 -05:00
Author
Owner
Copy Link

@nuxlear commented on GitHub (Jul 28, 2025):

Both transformers and llama.cpp now support EXAONE 4.0.

<!-- gh-comment-id:3125516096 --> @nuxlear commented on GitHub (Jul 28, 2025): Both transformers and llama.cpp now support EXAONE 4.0. - transformers: https://github.com/huggingface/transformers/releases/tag/v4.54.0 - llama.cpp: https://github.com/ggml-org/llama.cpp/releases/tag/b5932
GiteaMirror commented 2026-04-12 19:38:51 -05:00
Author
Owner
Copy Link

@zimdin12 commented on GitHub (Jul 31, 2025):

It seems that it is still not supported (latest ollama)
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'exaone4'

<!-- gh-comment-id:3140991172 --> @zimdin12 commented on GitHub (Jul 31, 2025): It seems that it is still not supported (latest ollama) llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'exaone4'
GiteaMirror commented 2026-04-12 19:38:51 -05:00
Author
Owner
Copy Link

@lgai-exaone commented on GitHub (Aug 4, 2025):

Is there any branch in progress? We’re looking forward to seeing support for EXAONE 4.0 in Ollama.

<!-- gh-comment-id:3148944938 --> @lgai-exaone commented on GitHub (Aug 4, 2025): Is there any branch in progress? We’re looking forward to seeing support for EXAONE 4.0 in Ollama.
GiteaMirror commented 2026-04-12 19:38:52 -05:00
Author
Owner
Copy Link

@zimdin12 commented on GitHub (Aug 5, 2025):

It doesn't seem so. vllm has support tho.

<!-- gh-comment-id:3155335030 --> @zimdin12 commented on GitHub (Aug 5, 2025): It doesn't seem so. vllm has support tho.
GiteaMirror commented 2026-04-12 19:38:52 -05:00
Author
Owner
Copy Link

@MichelRosselli commented on GitHub (Aug 11, 2025):

👀

<!-- gh-comment-id:3174492603 --> @MichelRosselli commented on GitHub (Aug 11, 2025): 👀
GiteaMirror commented 2026-04-12 19:38:53 -05:00
Author
Owner
Copy Link

@MichelRosselli commented on GitHub (Aug 15, 2025):

Finally, with release v0.11.5-rc2, support for the model has been added.

<!-- gh-comment-id:3191103870 --> @MichelRosselli commented on GitHub (Aug 15, 2025): Finally, with release [v0.11.5-rc2](https://github.com/ollama/ollama/releases/tag/v0.11.5-rc2), support for the model has been added.
GiteaMirror commented 2026-04-12 19:38:53 -05:00
Author
Owner
Copy Link

@illussna commented on GitHub (Feb 23, 2026):

We tested EXAONE 4.0 32B (Q4_K_M GGUF) via community Modelfile (ingu627/exaone4.0:32b) and confirmed basic chat works great.

However, EXAONE 4.0 officially supports agentic tool calling (per HF model card), but the current Ollama setup returns:
"does not support tools"

Would love to see official EXAONE 4.0 support with proper tool calling template. The model has great Korean + English quality and tool use would make it a strong local alternative.

Tested on: NVIDIA GB10 (128GB), Ollama latest

<!-- gh-comment-id:3947974208 --> @illussna commented on GitHub (Feb 23, 2026): We tested EXAONE 4.0 32B (Q4_K_M GGUF) via community Modelfile (ingu627/exaone4.0:32b) and confirmed basic chat works great. However, EXAONE 4.0 officially supports agentic tool calling (per HF model card), but the current Ollama setup returns: `"does not support tools"` Would love to see official EXAONE 4.0 support with proper tool calling template. The model has great Korean + English quality and tool use would make it a strong local alternative. Tested on: NVIDIA GB10 (128GB), Ollama latest
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#7547
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?