robbiemu/
qwen3-coder:30b-a3b-i-q4_K_XL

101 3 weeks ago

tools

3 weeks ago

b37ca1b42110 · 18GB ·

model
qwen3moe
·
30.5B
·
Q4_K_M
template
{{- /* Extract system message and other messages */ -}} {{- $system_message := "" -}} {{- $loop_mess
system
You are an interactive CLI tool that helps users with software engineering tasks. Use available tool
license
Apache License Version 2.0
params
{ "min_p": 0, "num_ctx": 65536, "repeat_penalty": 1.05, "stop": [ "<|im_star

Readme

This is unsloth’s popular quantization (https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF/blob/main/Qwen3-Coder-30B-A3B-Instruct-UD-Q4_K_XL.gguf) with tool calling based on the discussion: https://github.com/ggml-org/llama.cpp/issues/15012

Apologies about the num_ctx being lower than the model’s actual supported maximum.