The Local LLM Index / Quantization & Formats / #151

woct0rdho/transformers-qwen3-moe-fused

by woct0rdho · Quantization & Formats · updated 1mo ago

Fused Qwen3 MoE layer for faster training, compatible with Transformers, LoRA, bnb 4-bit quant, Unsloth. Also possible to train LoRA over GGUF

50
momentum
258
stars
17
forks
#151
rank
View on GitHub →