The mattshumer/Reflection-Llama-3.1-70B galaxy

31 models are built on mattshumer/Reflection-Llama-3.1-70B: 20 quantized, 4 fine-tuned, 0 adapters and 7 merges. Together they were downloaded 13,291 times in the last 30 days.

Most downloaded direct derivatives

• bartowski/Reflection-Llama-3.1-70B-GGUF (quantized), 1.5K downloads in 30 days
• legraphista/Reflection-Llama-3.1-70B-IMat-GGUF (quantized), 1.5K downloads in 30 days
• osanseviero/Reflection-Llama-3.1-70B-GGUF (quantized), 983 downloads in 30 days
• bullerwins/Reflection-Llama-3.1-70B-GGUF (quantized), 734 downloads in 30 days
• tensorblock/Reflection-Llama-3.1-70B-GGUF (quantized), 199 downloads in 30 days
• tdot604/Hazy-Llama-70b (merge), 22 downloads in 30 days
• nisten/Reflection-70b-PreciseQuant-6bpw-gguf (quantized), 21 downloads in 30 days
• Lucyfer1718/spartan_nemotron (merge), 18 downloads in 30 days
• Jolly-Q/Reflection-Llama-3.1-70B_BF16 (finetune), 17 downloads in 30 days
• Lucyfer1718/Spartan_Alpha-Powered_v2.0 (merge), 15 downloads in 30 days
• Orion-zhen/Reflection-Llama-3.1-70B-4.5bpw-exl2 (quantized), 10 downloads in 30 days
• bullerwins/Reflection-Llama-3.1-70B-bf16 (finetune), 10 downloads in 30 days
• amine-maazizi/llama-3-8b-chat-customer-support (finetune), 0 downloads in 30 days
• noname2112/Duster (finetune), 0 downloads in 30 days