answer bug
#18
by trentwang - opened
send any questions，answer is error
We need more context.
How are you running this? What application (or site, or space?) What settings are you using?
My hardware specifications are an AMD Ryzen 9 7950X3D CPU and an AMD Radeon RX 7900 XTX graphics card. I can run this model with GPU offloading.
I run Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf in LM Studio with default settings. When I send any message, the thought process appears as garbled text, and the responses are messy and incorrect.
After the Q8 quantization version failed to work properly, the Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf model runs normally.
This comment has been hidden (marked as Off-Topic)
trentwang changed discussion status to closed