The Intel/neural-chat-7b-v3-2 galaxy
9 models are built on Intel/neural-chat-7b-v3-2: 9 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 2,055 times in the last 30 days.
Most downloaded direct derivatives
- TheBloke/neural-chat-7B-v3-2-GGUF (quantized), 852 downloads in 30 days
- mradermacher/neural-chat-7b-v3-2-i1-GGUF (quantized), 516 downloads in 30 days
- mradermacher/neural-chat-7b-v3-2-GGUF (quantized), 233 downloads in 30 days
- brodatech/neural-chat-7B-v3-2-GGUF (quantized), 172 downloads in 30 days
- tensorblock/neural-chat-7b-v3-2-GGUF (quantized), 63 downloads in 30 days
- TheBloke/neural-chat-7B-v3-2-GPTQ (quantized), 25 downloads in 30 days
- DarkJanissary/neural-chat-7b-v3-2-Q6_K-GGUF (quantized), 18 downloads in 30 days
- llmware/intel-neural-chat-7b-v3-2-ov (quantized), 17 downloads in 30 days
- TheBloke/neural-chat-7B-v3-2-AWQ (quantized), 14 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.