The meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 galaxy
3 models are built on meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8: 3 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 27,458 times in the last 30 days.
Most downloaded direct derivatives
- chutesai/Llama-4-Maverick-17B-128E-Instruct-FP8 (quantized), 76 downloads in 30 days
- aarnphm/llama-4-maverick-17b-128e-instruct-fp8-sharded-tp8 (quantized), 21 downloads in 30 days
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8-Original (quantized), 6 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.