OPEA/Qwen2.5-0.5B-Instruct-int4-sym-inc

Quantization vs Qwen/Qwen2.5-0.5B-Instruct. OPEA/Qwen2.5-0.5B-Instruct-int4-sym-inc is a quantized version of the other (F16/I32).

On the Hub · Downloads on Model Pulse