Qwen/Qwen3.6-35B-A3B-FP8
Quantization vs Qwen/Qwen3.6-35B-A3B. Qwen/Qwen3.6-35B-A3B-FP8 is a quantized version of the other (F8_E4M3/BF16).
7 derivatives checked
- littlemex/prismyra-decision-qwen3.6-35b-a3b-fp8-36l: Partial fine-tune
- littlemex/prismyra-decision-qwen3.6-35b-a3b-nvfp4-36l: Partial fine-tune (fewer layers)
- EigenLabs/Qwen3.6-35B-A3B-MLX-mixed-4bit: Different architecture
- eme/Qwen3.6-35B-A3B-FP8-Q4_K_M-MTP-GUFF: Quantization
- goodasdgood/Qwen3.6-35B-A3B-FP8-Q2_K-GGUF: Not comparable yet
- Jerem62/Qwen3.6-35B-A3B-FP8-Q8_0-GGUF: Not comparable yet
- jokobaba/Qwen3.6-35B-A3B-FP8-Q4_K_M-GGUF: Not comparable yet