Models
GitHub
Discord
Turbo
Sign in
Download
Models
Download
GitHub
Discord
Sign in
mikepfunk28
/
deepseek8b_qwen3
27
Downloads
Updated
3 weeks ago
Using 4096 tokens for flash attention context window to work as intended. Trying a new template and system prompt to see how it reacts.
Using 4096 tokens for flash attention context window to work as intended. Trying a new template and system prompt to see how it reacts.
Cancel
tools
Name
1 model
Size
Context
Input
deepseek8b_qwen3:latest
77299afe1734
• 5.2GB • 128K context window •
Text input • 3 weeks ago
Text input • 3 weeks ago
deepseek8b_qwen3:latest
5.2GB
128K
Text
77299afe1734
· 3 weeks ago