The Kquant03/CognitiveFusion2-4x7B-BF16 galaxy

3 models are built on Kquant03/CognitiveFusion2-4x7B-BF16: 3 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 9,433 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/CognitiveFusion2-4x7B-BF16-i1-GGUF (quantized), 479 downloads in 30 days
• mradermacher/CognitiveFusion2-4x7B-BF16-GGUF (quantized), 238 downloads in 30 days
• tensorblock/CognitiveFusion2-4x7B-BF16-GGUF (quantized), 34 downloads in 30 days