bartowski

/

Qwen_Qwen3-0.6B-GGUF

like 19

ollama run hf.co/bartowski/Qwen_Qwen3-0.6B-GGUF:I
Q3_XXS
pulling manifest
pulling 4553e20544d2: 100% ▕█████████▏ 345 MB
pulling 41190096a061: 100% ▕█████████▏ 1.2 KB
pulling f401519675a9: 100% ▕█████████▏ 56 B
pulling 8ec9f4a2ff68: 100% ▕█████████▏ 549 B
verifying sha256 digest
writing manifest
success

what is 2+2





уверенность:

?
⠹

crazy shit you are

???


*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
^C

I think I am going to try this 0.6B model using transformer.js / vllm but I am on non cuda so vllm has an issue I don't know, and I actually wanted a chat app experience but I am not sure if transformer.js provides that