Hugging Face's logo

JANGQ-AI
/
Nemotron-3-Nano-Omni-30B-A3B-JANGTQ2

Image-Text-to-Text
MLX
English
nemotron
nemotron-h
mamba
mamba2
ssm
mixture-of-experts
multimodal
vision
audio
video
speech
omni
reasoning
jang
JANGTQ2
apple-silicon
Model card Files
xet
 Community
1
jangq commited on
Commit
2c6f6d4
·
verified ·
1 Parent(s): 3e751f8

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -63,7 +63,7 @@ Routed experts at **2-bit JANGTQ** — most compressed variant. 4-entry centroid
63
 
64
  | Variant | Size | Tok/s | Loader |
65
  |---|---:|---:|---|
66
- | [MXFP4](https://huggingface.co/JANGQ-AI/Nemotron-3-Nano-Omni-30B-A3B-MXFP4) | 22.6 GB | ~113 | `mlx_lm.load` |
67
  | [JANGTQ4](https://huggingface.co/JANGQ-AI/Nemotron-3-Nano-Omni-30B-A3B-JANGTQ4) | 19.9 GB | ~82 | `jang_tools.load_jangtq` |
68
  | [JANGTQ2](https://huggingface.co/JANGQ-AI/Nemotron-3-Nano-Omni-30B-A3B-JANGTQ2) | 12.6 GB | ~85 | `jang_tools.load_jangtq` |
69
 
 
63
 
64
  | Variant | Size | Tok/s | Loader |
65
  |---|---:|---:|---|
66
+ | [MXFP4 (Osaurus)](https://huggingface.co/OsaurusAI/Nemotron-3-Nano-Omni-30B-A3B-MXFP4) | 22.6 GB | ~113 | `mlx_lm.load` |
67
  | [JANGTQ4](https://huggingface.co/JANGQ-AI/Nemotron-3-Nano-Omni-30B-A3B-JANGTQ4) | 19.9 GB | ~82 | `jang_tools.load_jangtq` |
68
  | [JANGTQ2](https://huggingface.co/JANGQ-AI/Nemotron-3-Nano-Omni-30B-A3B-JANGTQ2) | 12.6 GB | ~85 | `jang_tools.load_jangtq` |
69