github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8007] EXAONE-3.5 2.4B, 7.8B, and 32B #5124

New Issue
Closed
opened 2026-04-12 16:13:28 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 16:13:28 -05:00
Owner
Copy Link

Originally created by @vYLQs6 on GitHub (Dec 9, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8007

https://huggingface.co/collections/LGAI-EXAONE/exaone-35-674d0e1bb3dcd2ab6f39dbb4

Note:

I enabled Q8 KV Cache, and when I tried the gguf uploaded by LG, I always get this error: Error: llama runner process has terminated: GGML_ASSERT(hparams.n_embd_head_k % ggml_blck_size(type_k) == 0) failed

Idk if this means this model just doesn't support kv cache or ollama needs an update.

Everything works fine after I disabled kv cache & flash attention

Models MT-Bench LiveBench Arena-Hard AlpacaEval IFEval KoMT-Bench[1] LogicKor
EXAONE 3.5 32B 8.51 43.0 78.6 60.6 81.7 8.05 9.06
Qwen 2.5 32B 8.49 50.6 67.0 41.0 78.7 7.75 8.89
C4AI Command R 32B 7.38 29.7 17.0 25.9 26.1 6.72 8.24
Gemma 2 27B 8.28 40.0 57.5 52.2 59.7 7.19 8.56
Yi 1.5 34B 7.64 26.2 23.1 34.8 55.5 4.88 6.33
Originally created by @vYLQs6 on GitHub (Dec 9, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8007 https://huggingface.co/collections/LGAI-EXAONE/exaone-35-674d0e1bb3dcd2ab6f39dbb4 --- Note: I enabled Q8 KV Cache, and when I tried the gguf uploaded by LG, I always get this error: `Error: llama runner process has terminated: GGML_ASSERT(hparams.n_embd_head_k % ggml_blck_size(type_k) == 0) failed` Idk if this means this model just doesn't support kv cache or ollama needs an update. Everything works fine after I disabled kv cache & flash attention --- <table> <tr> <th>Models</th> <th>MT-Bench</th> <th>LiveBench</th> <th>Arena-Hard</th> <th>AlpacaEval</th> <th>IFEval</th> <th>KoMT-Bench[1]</th> <th>LogicKor</th> </tr> <tr> <td>EXAONE 3.5 32B</td> <td align="center"><strong>8.51</strong></td> <td align="center">43.0</td> <td align="center"><strong>78.6</strong></td> <td align="center"><strong>60.6</strong></td> <td align="center"><strong>81.7</strong></td> <td align="center"><strong>8.05</strong></td> <td align="center"><strong>9.06</strong></td> </tr> <tr> <td>Qwen 2.5 32B</td> <td align="center">8.49</td> <td align="center"><strong>50.6</strong></td> <td align="center">67.0</td> <td align="center">41.0</td> <td align="center">78.7</td> <td align="center">7.75</td> <td align="center">8.89</td> </tr> <tr> <td>C4AI Command R 32B</td> <td align="center">7.38</td> <td align="center">29.7</td> <td align="center">17.0</td> <td align="center">25.9</td> <td align="center">26.1</td> <td align="center">6.72</td> <td align="center">8.24</td> </tr> <tr> <td>Gemma 2 27B</td> <td align="center">8.28</td> <td align="center">40.0</td> <td align="center">57.5</td> <td align="center">52.2</td> <td align="center">59.7</td> <td align="center">7.19</td> <td align="center">8.56</td> </tr> <tr> <td>Yi 1.5 34B</td> <td align="center">7.64</td> <td align="center">26.2</td> <td align="center">23.1</td> <td align="center">34.8</td> <td align="center">55.5</td> <td align="center">4.88</td> <td align="center">6.33</td> </tr> </table>
GiteaMirror added the model label 2026-04-12 16:13:28 -05:00
GiteaMirror commented 2026-04-12 16:13:30 -05:00
Author
Owner
Copy Link

@nonetrix commented on GitHub (Dec 10, 2024):

Dup of https://github.com/ollama/ollama/issues/6269 kinda, technically this includes more models though

<!-- gh-comment-id:2529895532 --> @nonetrix commented on GitHub (Dec 10, 2024): Dup of https://github.com/ollama/ollama/issues/6269 kinda, technically this includes more models though
GiteaMirror commented 2026-04-12 16:13:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 10, 2024):

https://ollama.com/library/exaone3.5

<!-- gh-comment-id:2530627186 --> @rick-github commented on GitHub (Dec 10, 2024): https://ollama.com/library/exaone3.5
GiteaMirror commented 2026-04-12 16:13:30 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Dec 10, 2024):

https://ollama.com/library/exaone3.5 (thanks @rick-github !)

<!-- gh-comment-id:2530729686 --> @jmorganca commented on GitHub (Dec 10, 2024): https://ollama.com/library/exaone3.5 (thanks @rick-github !)
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#5124
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?