Downloads · 30 days
710
42% of all-time downloads
divinetribe/Nemotron-3-Nano-Omni-30B-Abliterated-MM-bf16
Nemotron-3-Nano-Omni-30B-Abliterated-MM-bf16 is a image-text-to-text model from divinetribe. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as other.
⭐ 3.7k GitHub stars (github.com/nicedreamzapp) · ⬇️ 52.7k all-time downloads (huggingface.co/divinetribe)<br Source on GitHub: nicedreamzapp/nemotron-omni-mlx (⭐ 10+ stars) · this model ⬇️ 1.7k all-time downloads
Downloads · 30 days
710
42% of all-time downloads
All-time downloads
1.7K
Public
Parameters
33B
66 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors66 GB · 100%
From the Hugging Face model README
⭐ 3.7k GitHub stars (github.com/nicedreamzapp) · ⬇️ 52.7k all-time downloads (huggingface.co/divinetribe)<br> Source on GitHub: nicedreamzapp/nemotron-omni-mlx (⭐ 10+ stars) · this model ⬇️ 1.7k all-time downloads
<!-- live-stats:end -->Abliterated build of NVIDIA's tri-modal Nemotron-3-Nano-Omni-30B for Apple Silicon. Text, vision, and audio all work — the refusal direction was removed from the language stack only; the vision and sound towers are copied through untouched.
As far as I can tell this is the first abliterated Omni in MLX — the other uncensored builds are NVFP4 / GGUF and don't run on a Mac.
pip install -U mlx-vlm
python -m mlx_vlm generate --model divinetribe/Nemotron-3-Nano-Omni-30B-Abliterated-MM-bf16 \
--image your_image.jpg --prompt "Describe this image."
Needs a recent mlx-vlm (0.6.12+) with Omni support. Runtime reference:
https://github.com/nicedreamzapp/nemotron-omni-mlx
Not MLX-only. @wacomctl672 converted this to GGUF and ran it
in llama.cpp at Q4_K_M with the combined audio+vision mmproj from the ggml-org repository —
text, vision and audio all working. Ready-made weights:
wacomctl672/Nemotron-3-Nano-Omni-30B-Abliterated-MM-GGUF
If you convert it yourself, it needs one patch to llama.cpp/conversion/nemotron.py. Add this at
the top of modify_tensors (around line 431):
if "switch_mlp.fc1.weight" in name:
yield f"blk.{bid}.ffn_up_exps.weight", data_torch
return
elif "switch_mlp.fc2.weight" in name:
yield f"blk.{bid}.ffn_down_exps.weight", data_torch
return
Credit and details in discussion #1.
Directional ablation (Arditi et al.). The refusal direction on this model is spread
across two blocks (16 and 31), not one — a single-layer ablation leaves it refusing.
Both directions are Gram-Schmidt'd and orthogonalized out of every residual-writing
projection: mamba out_proj, attention o_proj, MoE routed-expert fc2, shared-expert
down_proj, plus the token embeddings.
Safety alignment has been removed. You are responsible for what you generate.
This model is one of the fighters in Claude Code Local (3.2k★), which runs Claude Code 100% on-device on Apple Silicon through an MLX-native Anthropic-API server. Not sure which local model to run as an agent? Check the Agent-12 local agent leaderboard: real agent tasks, judged by the filesystem, same hardware for every row.
Built by Matt Macosko in Humboldt, CA. Open to work on local-AI and Apple Silicon inference: [email protected].