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 #13565] add LFM2-2.6B-Exp from LiquidAI #34692

New Issue
Open
opened 2026-04-22 18:27:15 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-22 18:27:15 -05:00
Owner
Copy Link

Originally created by @scorpion7slayer on GitHub (Dec 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13565

https://huggingface.co/LiquidAI/LFM2-2.6B-Exp

Originally created by @scorpion7slayer on GitHub (Dec 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13565 https://huggingface.co/LiquidAI/LFM2-2.6B-Exp
GiteaMirror added the model label 2026-04-22 18:27:15 -05:00
GiteaMirror commented 2026-04-22 18:27:16 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 26, 2025):

$ ollama run hf.co/LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M
>>> hello
Hello! How can I assist you today?

Note there is a bug in the llama.cpp backend that breaks LFM2 models and currently these models can't be run with ollama 0.13.5, an earlier version must be used. The above example was 0.13.4.

<!-- gh-comment-id:3692041252 --> @rick-github commented on GitHub (Dec 26, 2025): ```console $ ollama run hf.co/LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M >>> hello Hello! How can I assist you today? ``` Note there is a [bug](https://github.com/ollama/ollama/issues/13529) in the llama.cpp backend that breaks LFM2 models and currently these models can't be run with ollama 0.13.5, an earlier version must be used. The above example was 0.13.4.
GiteaMirror commented 2026-04-22 18:27:16 -05:00
Author
Owner
Copy Link

@scorpion7slayer commented on GitHub (Dec 26, 2025):

oh okay but I think it can still be added to the ollama site because it has good benchmarks

<!-- gh-comment-id:3692728148 --> @scorpion7slayer commented on GitHub (Dec 26, 2025): oh okay but I think it can still be added to the ollama site because it has good benchmarks
GiteaMirror commented 2026-04-22 18:27:16 -05:00
Author
Owner
Copy Link

@duraiyuva commented on GitHub (Dec 31, 2025):

Not able to run on Android aarch64. Version 0.13.5. Below is output from Android. Any immediate fix?

ollama run [hf.co/liquidAI/LFM2-2.6B-GGUF](https://hf.co/liquidAI/LFM2-2.6B-GGUF)
Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'output_norm'
<!-- gh-comment-id:3701425030 --> @duraiyuva commented on GitHub (Dec 31, 2025): Not able to run on Android aarch64. Version 0.13.5. Below is output from Android. Any immediate fix? ``` ollama run [hf.co/liquidAI/LFM2-2.6B-GGUF](https://hf.co/liquidAI/LFM2-2.6B-GGUF) Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'output_norm' ```
GiteaMirror commented 2026-04-22 18:27:17 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 31, 2025):

Note there is a bug in the llama.cpp backend that breaks LFM2 models and currently these models can't be run with ollama 0.13.5, an earlier version must be used. The above example was 0.13.4.

<!-- gh-comment-id:3701447829 --> @rick-github commented on GitHub (Dec 31, 2025): > Note there is a bug in the llama.cpp backend that breaks LFM2 models and currently these models can't be run with ollama 0.13.5, an earlier version must be used. The above example was 0.13.4.
GiteaMirror commented 2026-04-22 18:27:17 -05:00
Author
Owner
Copy Link

@duraiyuva commented on GitHub (Dec 31, 2025):

Yes. It works in ollama 0.13.4. It is strange. For android phone, the Termux repo contains only the latest ollama 0.13.5. It seems the only possibility is to work with proot-distro. The bench mark created interest on the LFM's and it would be great if immediate fix is done.

<!-- gh-comment-id:3701755124 --> @duraiyuva commented on GitHub (Dec 31, 2025): Yes. It works in ollama 0.13.4. It is strange. For android phone, the Termux repo contains only the latest ollama 0.13.5. It seems the only possibility is to work with proot-distro. The bench mark created interest on the LFM's and it would be great if immediate fix is done.
GiteaMirror commented 2026-04-22 18:27:18 -05:00
Author
Owner
Copy Link

@Jobians commented on GitHub (Feb 22, 2026):

@duraiyuva any update on Termux?

<!-- gh-comment-id:3940526662 --> @Jobians commented on GitHub (Feb 22, 2026): @duraiyuva any update on Termux?
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#34692
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?