Qwen3.8-35B-A3B-Distill-oQ6e-mtp
This model was quantized using oQ (oMLX v0.7.0.dev2) mixed-precision quantization.
Quantization details
- Model type: qwen3_5_moe
- Bits: 6
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 609
Model size
36B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for funnygeeker/Qwen3.8-35B-A3B-Distill-oQ6e-mtp
Base model
Qwen/Qwen3.6-35B-A3B Finetuned
empero-ai/Qwen3.8-35B-A3B-Distill
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download funnygeeker/Qwen3.8-35B-A3B-Distill-oQ6e-mtp --local-dir Qwen3.8-35B-A3B-Distill-oQ6e-mtp