stewartpark/ qwen3.5:latest

1,390 2 months ago

Qwen3.5 model (27B dense) with always-on thinking, optimized for agentic coding, tool use, and browser automation.

vision tools thinking 27b
... /
params
9dff678302f3 · 133B
{
"min_p": 0,
"num_ctx": 262144,
"num_predict": 65536,
"presence_penalty": 1.5,
"repeat_penalty": 1,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}