meta-llama/Llama-3.1-70B-Instruct download history
meta-llama/Llama-3.1-70B-Instruct is a 70.6B-parameter text generation model by meta-llama. In the last 30 days it was downloaded 100,568 times (23,558 in the last 7 days), and 24,506,294 times in total.
It ranks #2,421 on the Hub by monthly downloads and #586 among text generation models.
It has 1,002 likes, 13 of them in the last week.
It is a fine-tune of meta-llama/Llama-3.1-70B.
1,674 models build on Llama-3.1-70B-Instruct: 983 quantized, 150 fine-tuned, 108 adapters and 433 merges. Together with the original they were downloaded 907,348 times in the last 30 days. See the Llama-3.1-70B-Instruct galaxy.
Most downloaded derivatives
- RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8 (quantized), 138.8K downloads in 30 days
- MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF (quantized), 137.7K downloads in 30 days
- bartowski/Meta-Llama-3.1-70B-Instruct-GGUF (quantized), 95.1K downloads in 30 days
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF (finetune), 24.8K downloads in 30 days
- RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a16 (quantized), 9.1K downloads in 30 days
- unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit (quantized), 5.8K downloads in 30 days
- unsloth/Meta-Llama-3.1-70B-Instruct (quantized), 4.9K downloads in 30 days
- nvidia/Llama-3.1-70B-Instruct-FP8 (finetune), 3.1K downloads in 30 days
- amd/Llama-3.1-70B-Instruct-FP8-KV (quantized), 2.5K downloads in 30 days
- legraphista/Meta-Llama-3.1-70B-Instruct-IMat-GGUF (quantized), 2K downloads in 30 days
- mradermacher/Meta-Llama-3.1-70B-Instruct-GGUF (quantized), 1.6K downloads in 30 days
- qwp4w3hyb/Meta-Llama-3.1-70B-Instruct-iMat-GGUF (quantized), 1.6K downloads in 30 days