ExpedientFalcon/
Qwen3-4B-UD-Q5_K_XL:latest

91 5 months ago

Qwen3-4B Q5_K_XL Unsloth UD 2.0 adaptively quantized model, much better for coding than vanilla Q4_K_M quants without taking up the VWAM of an 8-bit Q8_0 model. From https://huggingface.co/unsloth/Qwen3-4B-GGUF/tree/main

tools

5 months ago

f5bc81c7b7e3 · 2.9GB ·

model
qwen3
·
4.02B
·
Q5_K_M
params
{ "min_p": 0, "num_ctx": 40960, "num_predict": 16384, "repeat_penalty": 1, "stop
template
{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{

Readme

No readme