Nemotron 3 Nano Omni 30B A3B JANGTQ4 CRACK

--- license: other license_name: nvidia-open-model-license license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license base_model: nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning pipeline_tag: any-to-any language: - en - multilingual library_name: mlx tags: - nemotron - nemotron-h - mlx - jangtq - crack - abliterated - uncensored - multimodal - vision - audio - speech - mamba-2 - moe - reasoning - thinking - harmbench - radio-vit - parakeet thumbnail: dealign_mascot.png --- > **Reasoning V3 SKU.** Loads via **[vMLX](https://vmlx.net)** or `jang-tools` Python. Follow [@dealignai](https://x.com/dealignai). --- <div align="center"> <a href="https://vmlx.net"> <img src="vmlx-app.png" alt="vMLX — run JANG models on Apple Silicon" width="820" /> <br/> <strong>Built for vMLX</strong> — the only MLX inferencer with VL support, KV cache quantization, prefix cache reuse, agentic tool calling, and speculative decoding. <br/> _{Free for macOS · <strong>vmlx.net</strong>} </a> </div> <h3 align="center">⚡ All JANG models are meant to be run in <a href="https://vmlx.net">vMLX</a></h3> --- <div align="center"> <img src="dealign_mascot.png" width="128" /> # Nemotron-3-Nano-Omni-30B-A3B — JANGTQ4 + CRACK v2 **JANGTQ4** (8-bit attn affine + 4-bit MXTQ routed experts) | **CRACK abliterated v2** | Vision + Audio (Speech) | Hybrid Mamba-2 + Attn + MoE | **19 GB** <a href="https://ko-fi.com/dealignai"><img src="https://img.shields.io/badge/Ko--fi-Support_Development-FF5E5B?logo=ko-fi&logoColor=white&style=for-the-badge" alt="Ko-fi"></a> </div> --- ## Headline numbers | Metric | This v2 model | Base model | Δ | |---|---|---|---| | HarmBench-320 strict comply (thinking=ON) | **97.2%** (311/320) | 12.81% (refuses) | **+84.4pp** | | MMLU-200 generative (thinking=ON, max=8000) | **74.0%** (148/200) | 86.5% (max=2000) | -12.5pp | | Refusals on harmful prompts | **0** explicit refuses | typically 90%+ refuse | abliteration complete | | `</think>` close at greedy on hard MMLU | **5/5** | 5/5 | preserved | | Multi-turn (3-turn escalation × 3 conversations) | **9/9** comply, context preserved | n/a | works | | Multimodal byte-identical to base | preserved | — | preserved | | Bundle size | 19 GB | 66 GB BF16 | — | | Context | 262,144 tokens native | same | preserved | > The 12.5pp MMLU gap is concentrated in two reasoning-heavy...

Source context: 127 downloads · 2 likes · Pipeline any-to-any · Library mlx · Repo dealignai/Nemotron-3-Nano-Omni-30B-A3B-JANGTQ4-CRACK