club-3090 adds experimental FP8 support for Qwen3.6-27B!
The club-3090 project has introduced experimental FP8 quantization support for the Qwen3.6-27B model. This new feature is particularly relevant for users operating dual RTX 3090 graphics card setups. The performance of the FP8 quantized model is reported to be nearly identical to the original unquantized BF16 version. AI
IMPACT Enables more efficient local inference for a specific large language model on consumer hardware.