Prioritized ctx over bpw for this one since it's primarily an agentic model. Would recommend Gemma 4 31B instead for non-agentic.
5.10 bpw, a mixture of Q5_K and Q4_K
Fits ~90k F16, ~170k Q8 CTX on a 24GiB GPU using Vulkan
Prioritized ctx over bpw for this one since it's primarily an agentic model. Would recommend Gemma 4 31B instead for non-agentic.
5.10 bpw, a mixture of Q5_K and Q4_K
Fits ~90k F16, ~170k Q8 CTX on a 24GiB GPU using Vulkan
有文件?提交种子。
提交种子Qwen/Qwen3.6-27B