GitHub
183.4K
Download
Models
Docs
Pricing
Sign in
Download
Models
Docs
Pricing
Sign in
denisavetisyan
/
gemma4-31b-q4_0-24gb-48k
:latest
23
Downloads
Updated
1 week ago
Production-ready copy of gemma4:31b-hf-qat-think (Unsloth QAT UD-Q4_K_XL, 30.7B) with battle-tested defaults baked in: temperature 1.0, top_p 0.95, top_k 64, num_ctx 48384. Sized for a single 24 GB GPU.
Production-ready copy of gemma4:31b-hf-qat-think (Unsloth QAT UD-Q4_K_XL, 30.7B) with battle-tested defaults baked in: temperature 1.0, top_p 0.95, top_k 64, num_ctx 48384. Sized for a single 24 GB GPU.
Cancel
vision
tools
thinking
gemma4-31b-q4_0-24gb-48k:latest
...
/
params
6b521bca645d ยท 149B
{
"num_ctx": 48384,
"stop": [
"<bos>",
"<|turn>",
"<turn|>",
"<|turn>user"
],
"temperature": 1,
"top_k": 64,
"top_p": 0.95
}