QwexGP/QAi-2.0

Quantization vs unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit. unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).

2 derivatives checked

• mradermacher/QAi-2.0-i1-GGUF: Quantization
• mradermacher/QAi-2.0-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse