EXL2 Quantizations of Llama-3.2-1B-Instruct
Using exllamav2 release 0.2.5 for quantization.
Original model: https://huggingface.co/Qwen/Qwen2.5-Coder-3B
Bits 8.0, lm_head 8.0
EXL2 Quantizations of Llama-3.2-1B-Instruct
Using exllamav2 release 0.2.5 for quantization.
Original model: https://huggingface.co/Qwen/Qwen2.5-Coder-3B
Bits 8.0, lm_head 8.0