Downloads · 30 days
0
jockey1011/DeepQwen-3B-Uncensored-GGUF
DeepQwen-3B-Uncensored-GGUF is a machine learning model from jockey1011. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for gguf. The card lists the license as apache-2.0.
This is a specialized 3B parameter model designed for high-performance coding and reasoning on low-VRAM hardware (RTX 3050/3060 etc).
Downloads · 30 days
0
Access
Public
Updated Dec 31, 2025
Repo size
—
Likes
2
Public
Click a slice to open those files.
.md2.4 KB · 61%
From the Hugging Face model README
This is a specialized 3B parameter model designed for high-performance coding and reasoning on low-VRAM hardware (RTX 3050/3060 etc).
It combines the speed of Qwen 2.5, the reasoning power of DeepSeek R1, and surgical uncensoring (ablit) to create a compliant, thinking coding assistant.
<think> block where it plans logic, checks for bugs, and reasons before writing code.Run with high context for best results:
./llama-server \
-m qwen-r1-uncensored-q5_k_m.gguf \
--ctx-size 8192 \
--n-gpu-layers 100 \
-fa
<|im_start|>system
You are a reasoning model. Think step-by-step before answering.<|im_end|>
<|im_start|>user
Write a Python script to scan a network for open ports.<|im_end|>
<|im_start|>assistant
<think>
User wants a port scanner.
I should use the socket library.
I need to handle timeouts and threading for speed.
</think>
Here is the script...