Qwen3.5-122B-A10B-oQ4
This model was quantized using oQ mixed-precision quantization.
Quantization details
- Model type: qwen3_5_moe
- Bits: 4
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 59
Model size
20B params
Tensor type
U8
路
U32 路
BF16 路
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.5-122B-A10B-oQ4 latent-variable/Qwen3.5-122B-A10B-oQ4