To the dozens of 3x 3090 Local LLM people - I found our current best fit
英文标题：To the dozens of 3x 3090 Local LLM people - I found our current best fit
I have been anti-low quant. I can feel the difference, I swear. I am also anti-quantized KV cache. I have been burned there - I think the tradeoffs compound, especially at longer contexts. Due to this, I have been running Qwen 3.8 27B (UD-Q8_K_L) on 2x of the 3090s in TP. I swear by it. It is
打开原文相关 9 · 机会 1
中文
I have been anti-low quant. I can feel the difference, I swear. I am also anti-quantized KV cache. I have been burned there - I think the tradeoffs compound, especially at longer contexts. Due to this, I have been running Qwen 3.8 27B (UD-Q8_K_L) on 2x of the 3090s in TP. I swear by it. It is
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
I have been anti-low quant. I can feel the difference, I swear. I am also anti-quantized KV cache. I have been burned there - I think the tradeoffs compound, especially at longer contexts. Due to this, I have been running Qwen 3.8 27B (UD-Q8_K_L) on 2x of the 3090s in TP. I swear by it. It is