Models
GitHub
Discord
Docs
Cloud
Sign in
Download
Models
Download
GitHub
Discord
Docs
Cloud
Sign in
pielee
/
qwen3-4b-thinking-2507_q8
:latest
409
Downloads
Updated
3 months ago
Qwen3-4B-Thinking-2507_q8: A 4-billion-parameter inference model with 8-bit quantization, optimized for efficient reasoning in resource-constrained environments.
Qwen3-4B-Thinking-2507_q8: A 4-billion-parameter inference model with 8-bit quantization, optimized for efficient reasoning in resource-constrained environments.
Cancel
tools
thinking
qwen3-4b-thinking-2507_q8:latest
...
/
params
cff3f395ef37 · 120B
{
"repeat_penalty": 1,
"stop": [
"<|im_start|>",
"<|im_end|>"
],
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}