13 1 97

Hangou Fanou

Hugs4Llamas

AI & ML interests

None yet

Recent Activity

liked a model 14 days ago

Yuma42/Llama3.1-DeepDilemma-V1-8B

liked a model 14 days ago

Yuma42/Llama3.1-DeepDilemma-V1-8B-Q4_K_S-GGUF

liked a model 2 months ago

nvidia/AceReason-Nemotron-7B

View all activity

Organizations

None yet

liked 2 models 14 days ago

Yuma42/Llama3.1-DeepDilemma-V1-8B

8B • Updated 19 days ago • 3 • 1

Yuma42/Llama3.1-DeepDilemma-V1-8B-Q4_K_S-GGUF

8B • Updated 19 days ago • 40 • 1

liked a model 2 months ago

nvidia/AceReason-Nemotron-7B

Text Generation • 8B • Updated Jun 17 • 3.82k • • 18

liked 2 models 3 months ago

deepcogito/cogito-v1-preview-llama-8B

Text Generation • 8B • Updated Apr 8 • 1.79k • • 48

mradermacher/Llama-3.1-Nemotron-Nano-8B-v1-abliterated-Uncensored-Toxic-DPO-GGUF

8B • Updated 29 days ago • 297 • 3

liked a Space 3 months ago

RWKV HF Space

🐦

Generate text based on input prompts

New activity in unsloth/Qwen3-8B-GGUF 3 months ago

Q4ks

#2 opened 3 months ago by

Hugs4Llamas

replied to bartowski's post 3 months ago

Hello Bartowski, you seem to know a lot about the gguf format and llamacpp, maybe you know why the bug in this issue happens which came with the switch to the Q4_0 format? The maintainer had to close the issue because he wasn't able to locate/fix the problem, I was among those who did use your Q4_0_4_4, but with this bug there is no way of benefiting from Q4_0 on edge devices. If you have an idea I would appreciate it you could hint the dev about it.

The issue I'm talking about:
https://github.com/Vali-98/ChatterUI/issues/209

liked a model 3 months ago