pdurugyan/ qwen3.5-9b-deepseek-v4-flash-Q4_K_M:latest

975 1 week ago

Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4.

tools thinking
... /
params
69633c44073e · 63B
{
"repeat_penalty": 1.1,
"temperature": 1,
"top_k": 20,
"top_p": 0.95
}