Ornith-1.0-35B-Qwen3.6MTP-oQ4
This model was quantized using oQ (oMLX v0.5.1) mixed-precision quantization.
Quantization details
- Model type: qwen3_5_moe
- Bits: 4
- Group size: 64
- Format: MLX safetensors
Overview
This is a hybrid mixed-precision oQ4 quantization of the agentic coding model Ornith-1.0-35B, grafted with the high-efficiency Multi-Token Prediction (MTP) lookahead blocks from Qwen3.6-35B-A3B.
- Downloads last month
- 147
Model size
6B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for blackfan23/Ornith-1.0-35B-Qwen3.6MTP-oQ4
Base model
ornith-ai/Ornith-1.0-35B
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Ornith-1.0-35B-Qwen3.6MTP-oQ4 blackfan23/Ornith-1.0-35B-Qwen3.6MTP-oQ4