The vllm-sr/vela3-fast galaxy
2 models are built on vllm-sr/vela3-fast: 2 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 2,245 times in the last 30 days.
Most downloaded direct derivatives
- FluidInference/vela-3.0-coreml (quantized), 151 downloads in 30 days
- diakrisis/espresso-380m (quantized), 6 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.