FabioTrindade/Llama-3.1-8B-Instruct-W4A4KV8-NVFP4-SpQ-R1R2-SmQ-0.5-KVS-attn_head download history
FabioTrindade/Llama-3.1-8B-Instruct-W4A4KV8-NVFP4-SpQ-R1R2-SmQ-0.5-KVS-attn_head is a 5.0B-parameter model model by FabioTrindade. In the last 30 days it was downloaded 36 times (6 in the last 7 days), and 372 times in total.
It ranks #289,445 on the Hub by monthly downloads.
It has 0 likes.
It is a quantization of meta-llama/Llama-3.1-8B-Instruct.
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.