948 5 days ago

Qwen3.8-9B-Distill is a dense 9B reasoning model: it brings the reasoning behaviour of a frontier-scale teacher (Qwen3.8, 2.4T-A95B) into a model that fits on a single consumer GPU. Every answer opens with a <think> block learned from real teacher traces,

vision tools thinking
47dfa152940a · 63B
{
"repeat_penalty": 1,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}