GitHub
183.4K
Download
Models
Docs
Pricing
Sign in
Download
Models
Docs
Pricing
Sign in
denisavetisyan
/
gemma4-31b-q4_0-24gb-48k
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
Name
1 model
Size / Usage
Context
Input
gemma4-31b-q4_0-24gb-48k:latest
20ee302d8c00
• 18GB • 256K context window •
Text, Image input • 1 week ago
Text, Image input • 1 week ago
gemma4-31b-q4_0-24gb-48k:latest
18GB
256K
Text, Image
20ee302d8c00
· 1 week ago