Custom GGUF quant for : | |
failspy/llama-3-70B-Instruct-abliterated-GGUF | |
IQ4_SR is Optimal (8k ctx) for 36GB VRAM with an IGP displaying the OS. | |
IQ4_MR is optimal for the same config with MMQ and KV quants (8 bits) | |
Without an IGP, the IQ4_XSR is for you. |