The codefuse-ai/F2LLM-v2-4B galaxy
6 models are built on codefuse-ai/F2LLM-v2-4B: 5 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 41,356 times in the last 30 days.
Most downloaded direct derivatives
- mradermacher/F2LLM-v2-4B-GGUF (quantized), 451 downloads in 30 days
- VelociQ8/F2LLM-v2-4B-Q8A64-GGUF (quantized), 161 downloads in 30 days
- fcmeyer/F2LLM-v2-4B-mlx-8bit (quantized), 62 downloads in 30 days
- seamon67/F2LLM-v2-4B-GGUF (quantized), 55 downloads in 30 days
- fcmeyer/F2LLM-v2-4B-mlx-6bit (quantized), 34 downloads in 30 days
- fcmeyer/F2LLM-v2-4B-mlx-bf16 (finetune), 31 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.