What are the hardware requirements for QwenDGAF Coder 3B?

QwenDGAF Coder 3B requires approximately 1.9 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed QwenDGAF Coder 3B and how large is it?

QwenDGAF Coder 3B is developed by hecan3d, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate QwenDGAF Coder 3B?

QwenDGAF Coder 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

QwenDGAF Coder 3B by hecan3d — VRAM 1.9GB, 32K context

Name: QwenDGAF Coder 3B
Author: hecan3d

QwenDGAF Coder 3B is an open-source language model by hecan3d. Features: 3b LLM, VRAM: 1.9GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, Code Generating.

Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-coder-... Code Code-review Codegen Coding-assistant Conversational En Endpoints compatible Gguf Humor Instruct Lazy-ai Llama-cpp Quantized Qwen2 Qwen2.5-coder Region:us Roleplay Ru Slacker Uncensored Unsloth Zh

Model Card on HF 🤗: https://huggingface.co/hecan3d/QwenDGAF-Coder-3B

QwenDGAF Coder 3B Parameters and Internals

LLM Name	QwenDGAF Coder 3B
Repository 🤗	https://huggingface.co/hecan3d/QwenDGAF-Coder-3B
Base Model(s)	Qwen/Qwen2.5-Coder-3B-Instruct Qwen/Qwen2.5-Coder-3B-Instruct
Model Size	3b
Required VRAM	1.9 GB
Updated	2026-10-22
Maintainer	hecan3d
Model Type	qwen2
Instruction-Based	Yes
Model Files	6.2 GB 1.9 GB 2.5 GB 3.3 GB
Supported Languages	ru en zh
GGUF Quantization	Yes
Quantization Type	gguf
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Vocabulary Size	151936
Torch Data Type	bfloat16

Rank the QwenDGAF Coder 3B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to QwenDGAF Coder 3B

Best Alternatives	Context / RAM	Downloads	Likes
VibeThinker 3B Heretic	128K / 6.2 GB	1016	4
LaboAI 0.4.0 3B	32K / 6.2 GB	150	1
TINY THINKER INSTRUCT	32K / 6.2 GB	1382	4
...n2.5 Coder 3B Instruct Heretic	32K / 6.2 GB	2410	1
Coder GRPO 3B	32K / 6.2 GB	298	7
Tiny Agent A 3B	32K / 6.2 GB	526	24
Qwen Manim Animation 16bit	32K / 6.2 GB	19	0
...wen2.5 Coder 3B Instruct V13.1	32K / 6.2 GB	93	0
...2.5 Coder 3B Instruct Bnb 4bit	32K / 2 GB	19150	7
Qwen2.5 Coder 3B Instruct 4bit	32K / 1.7 GB	1621	2

Note: green Score (e.g. "73.2") means that the model is better than hecan3d/QwenDGAF-Coder-3B.