This quantization was uploaded on 2026-06-29 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
Ornith-1.0-35B-oQ6-fp16
This model was quantized using oQ (oMLX v0.4.5.dev1) mixed-precision quantization.
Quantization details
- Model type: qwen3_5_moe
- Bits: 6
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 34
Model size
8B params
Tensor type
F16
路
U32 路
F32 路
Hardware compatibility
Log In to add your hardware
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support
Model tree for kreeger/Ornith-1.0-35B-oQ6-fp16
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-oQ6-fp16 kreeger/Ornith-1.0-35B-oQ6-fp16