--- license: mit license_link: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B/blob/main/LICENSE thumbnail: https://huggingface.co/AtomicChat/ornith-35b-MLX-8bit/resolve/main/hero.png base_model: - deepreinforce-ai/Ornith-1.0-35B base_model_relation: quantized quantized_by: AtomicChat pipeline_tag: text-generation library_name: mlx tags: - atomic-chat - ornith - deepreinforce-ai - mlx - apple-silicon - quantized ---

Base model: deepreinforce-ai/Ornith-1.0-35B

**Ornith 1.0 35B**, self-quantized to MLX by [Atomic Chat](https://atomic.chat). Built straight from DeepReinforce's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. ## Highlights - **0.0B parameters**: the weights this repo quantizes. - **Context length**: 262,144 tokens (256K), as published by DeepReinforce. - **40 layers**: Mixture-of-Experts. - **Modalities**: Text, Image. - **Full imatrix ladder**: every quant is calibrated with an importance matrix. - **State-of-the-Art Coding Agents**: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw. - **Self-Improving Training Framework**: Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model discovers better search trajectories and generates higher-quality solutions. > [!NOTE] > These MLXs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model. ## Model Overview | Property | Value | |---|---| | Base model | `deepreinforce-ai/Ornith-1.0-35B` | | Parameters | 0.0B | | Layers | 40 | | Experts | 256 routed (top-8) | | Context length | 262,144 tokens (256K) | | Vocabulary | 248,320 | | Modalities | Text, Image | | Architecture | Mixture-of-Experts, 256 experts (top-8), 16 attention heads over 2 KV heads, `Qwen3_5MoeForConditionalGeneration` | | This repo | MLX weights | ## Get started - **[Atomic Chat](https://atomic.chat):** search `AtomicChat/ornith-35b-MLX-8bit` and hit **Use this model**. - **mlx-lm:** `mlx_lm.generate --model AtomicChat/ornith-35b-MLX-8bit --prompt "Hello" --max-tokens 512` - **Server:** `mlx_lm.server --model AtomicChat/ornith-35b-MLX-8bit --port 8080` ## Best practices | Parameter | Value | |---|---| | temperature | 1.0 | | top_p | 1.0 | | top_k | 20 | DeepReinforce's recommended sampling configuration for `deepreinforce-ai/Ornith-1.0-35B`. ## How these were made 1. Download `deepreinforce-ai/Ornith-1.0-35B` (original weights). 2. Convert and quantize with `mlx_lm.convert` on our pipeline. ## License Original model by DeepReinforce, released under the MIT license. Full terms: [MIT](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B/blob/main/LICENSE). Quantized by Atomic Chat.