alt Hacker Newsqwen3 is slow though. i used it. it worked, but it was slow and lacking features.
Replies
xfalcox • last Monday at 12:17 AM
Qwen 3 is not slow by any metrics.
Which model, inference software and hardware are you running it on?
The 30BA3B variant flies on any GPU.
SchemaLoad • last Monday at 2:06 AM
GPT-OSS is slow too. Gemma3 gives me better results and runs faster.
On my RTX 5090 with llama.cpp:
gpt-oss 120B - 37 tok/sec (with CPU offloading, doesn't fit in the GPU entirely)
Qwen3 32B - 65 tok/sec
Qwen3 30B-A3B - 150 tok/sec
(all at 4-bit)