Qwen3.6-27B - Effect of KV quantization on KLD - Q8, Q6, Q5 (bartowski)
英文标题:Qwen3.6-27B - Effect of KV quantization on KLD - Q8, Q6, Q5 (bartowski)
Lower is better - Quantization increases from right to left I recently made a post here about how I squeezed more context into a Q8 model of bartowski's Qwen3.6-27B. My reasoning was that in my (anecdotal) experience, a Q8 has been performing a lot better than a Q6 or a Q5. There were a lot of
打开原文相关 2 · 机会 0
中文
Lower is better - Quantization increases from right to left I recently made a post here about how I squeezed more context into a Q8 model of bartowski's Qwen3.6-27B. My reasoning was that in my (anecdotal) experience, a Q8 has been performing a lot better than a Q6 or a Q5. There were a lot of
中文全文翻译正在补齐,可先查看下方英文原文。
English / 原文
Lower is better - Quantization increases from right to left I recently made a post here about how I squeezed more context into a Q8 model of bartowski's Qwen3.6-27B. My reasoning was that in my (anecdotal) experience, a Q8 has been performing a lot better than a Q6 or a Q5. There were a lot of