exolabs/qwen3-6-27b-mlx-8bit-text-dequant-bf16
Private dequantized BF16 export for vLLM validation.
- Internal model id:
qwen3-6-27b-mlx-8bit - MLX source:
unsloth/Qwen3.6-27B-MLX-8bit - Original HF comparison model:
Qwen/Qwen3.6-27B - Export dtype:
bfloat16 - Text-only export:
False
This checkpoint is the result of dequantizing the quantized MLX checkpoint. It is not the original upstream BF16 checkpoint.
- Downloads last month
- 22
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support