SetneufPT/ Qwen3.6-27B-CODER-MTP_Q4_105k_24GB-GPU:latest

3 an hour ago

Custom model for coding with agents to use locally with 24gb GPUs (working very fine...)

vision tools thinking
... /
params
8967a3145683 · 147B
{
"draft_num_predict": 4,
"min_p": 0,
"num_ctx": 105000,
"num_gpu": 999,
"presence_penalty": 0,
"repeat_penalty": 1,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}