[!IMPORTANT] This quantization was uploaded on 2026-07-22 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

rlm-qwen3-8b-v0.1-oQ6e-fp16

Quantization details

• Model type: qwen3
• Bits: 6
• Group size: 64
• Format: MLX safetensors