The Cheng98/llama-39m galaxy
1 models are built on Cheng98/llama-39m: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 405 times in the last 30 days.
Most downloaded direct derivatives
- tensorblock/llama-39m-GGUF (quantized), 6 downloads in 30 days