Models
GitHub
Discord
Docs
Cloud
Sign in
Download
Models
Download
GitHub
Discord
Docs
Cloud
Sign in
pielee
/
qwen3-4b_q8
:latest
141
Downloads
Updated
3 months ago
A 4B-parameter, 8-bit quantized inference model with /think (reasoning) and /no_think (fast response) modes.
A 4B-parameter, 8-bit quantized inference model with /think (reasoning) and /no_think (fast response) modes.
Cancel
tools
thinking
Updated 3 months ago
3 months ago
460978f23904 · 4.3GB ·
model
arch
qwen3
·
parameters
4.02B
·
quantization
Q8_0
4.3GB
template
{{- $lastUserIdx := -1 -}} {{- range $idx, $msg := .Messages -}} {{- if eq $msg.Role "user" }}{{ $la
1.5kB
system
你是Qwen3, 由阿里巴巴公司训练发布. 你乐于帮助用户解决问题.
82B
params
{ "repeat_penalty": 1, "stop": [ "<|im_start|>", "<|im_end|>" ], "te
120B
Readme
No readme
Write
Preview
Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)