Falcon 7B/40B is good, but hasn't really caught on like LLaMA has. One big reason is that its not well supported by 4-bit inference code (namely llama.cpp and GPTQ).

Mosaic's 7B (and 30B?) models have the same issue, and 7B kinda paled in comparison to LLaMA 7B... But maybe it would be better if finetuned?

To me, its kinda baffling that Mosaic didn't work on adding highly quantized inference to the popular frameworks.