second_constantine/
qwen3-coder-A3B:30b

77 4 weeks ago

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud. (quantized Q4_K_M)

tools 30b

4 weeks ago

4745e8592927 · 19GB

model
qwen3moe
·
30.5B
·
Q4_K_M
template
{{- $lastUserIdx := -1 -}} {{- range $idx, $msg := .Messages -}} {{- if eq $msg.Role "user" }}{{ $la
params
{ "repeat_penalty": 1, "stop": [ "<|im_start|>", "<|im_end|>" ], "te

Readme

Based on the https://huggingface.co/lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-GGUF, but with support for tools added (Modelfile changed)

Feature Value
VLM false
think false
tools true
speed 102 token/s

The characteristics are approximate, tested on rtx3090 24GB