The Qwen/Qwen3.6-27B-FP8 galaxy
10 models are built on Qwen/Qwen3.6-27B-FP8: 7 quantized, 1 fine-tuned, 2 adapters and 0 merges. Together they were downloaded 1,174,786 times in the last 30 days.
Most downloaded direct derivatives
- furiosa-ai/Qwen3.6-27B-FP8 (quantized), 584 downloads in 30 days
- gaoqianshen/Qwen3.6-27B-FP8-Q4_K_M-GGUF (quantized), 131 downloads in 30 days
- lokeshe09/Qwen3.6-27B-FP8_OCRR (finetune), 66 downloads in 30 days
- LogicBombaklot/Qwen3.6-27B-RYS-XL-GGUF (quantized), 25 downloads in 30 days
- inferRouter/Qwen3.6-27B-FP8-lmhead-fp8 (quantized), 25 downloads in 30 days
- Alex89912/Qwen3.6-27B-FP8-Q4_K_M-GGUF (quantized), 22 downloads in 30 days
- inferRouter/Qwen3.6-27B-FP8-lmhead-embed-fp8 (quantized), 11 downloads in 30 days
- GrahamMiranda/Graham-Miranda (quantized), 7 downloads in 30 days
- haielab/Qwen3.6-27B-LoRA-fermipy (adapter), 6 downloads in 30 days
- haielab/Qwen3.6-27B-LoRA-fermipy-clean (adapter), 5 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.