meta-llama/Llama-3.1-405B-Instruct download history
meta-llama/Llama-3.1-405B-Instruct is a 405.9B-parameter text generation model by meta-llama. In the last 30 days it was downloaded 12,733 times (2,193 in the last 7 days), and 4,285,069 times in total.
It ranks #7,292 on the Hub by monthly downloads and #1,642 among text generation models.
It has 604 likes, 2 of them in the last week.
It is a fine-tune of meta-llama/Llama-3.1-405B.
80 models build on Llama-3.1-405B-Instruct: 42 quantized, 26 fine-tuned, 12 adapters and 0 merges. Together with the original they were downloaded 164,944 times in the last 30 days. See the Llama-3.1-405B-Instruct galaxy.
Most downloaded derivatives
- MaziyarPanahi/Meta-Llama-3.1-405B-Instruct-GGUF (quantized), 135.3K downloads in 30 days
- nvidia/Llama-3.1-405B-Instruct-FP8 (finetune), 6.6K downloads in 30 days
- RedHatAI/Meta-Llama-3.1-405B-Instruct-FP8-dynamic (quantized), 1.8K downloads in 30 days
- amd/Llama-3.1-405B-Instruct-FP8-KV (quantized), 1.8K downloads in 30 days
- nvidia/Llama-3.1-405B-Instruct-NVFP4 (finetune), 1.7K downloads in 30 days
- amd/Llama-3.1-405B-Instruct-MXFP4-Preview (quantized), 670 downloads in 30 days
- RedHatAI/Meta-Llama-3.1-405B-Instruct-FP8 (quantized), 552 downloads in 30 days
- etemiz/Llama-3.1-405B-Inst-GGUF (quantized), 410 downloads in 30 days
- meta-llama/Llama-3.1-405B-Instruct-FP8 (quantized), 354 downloads in 30 days
- RedHatAI/Meta-Llama-3.1-405B-Instruct-quantized.w4a16 (quantized), 322 downloads in 30 days
- nisten/meta-405b-instruct-cpu-optimized-gguf (quantized), 272 downloads in 30 days
- mlabonne/BigLlama-3.1-681B-Instruct (finetune), 188 downloads in 30 days