LLM EXPLORER 66,704 MODELS INDEXED

QwenDGAF 2 4B by hecan3d

By hecan3d · 348 downloads
HF Repo ↗ Copy URL

QwenDGAF 2 4B is an open-source language model by hecan3d. Features: 4b LLM, VRAM: 1.8GB, Context: 256K, License: apache-2.0, Quantized, Instruction-Based.

Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-4b   Conversational   En   Endpoints compatible   Gguf   Humor   Instruct   Lazy-ai   Llama-cpp   Multi-turn   Quantized   Qwen3   Region:us   Roleplay   Ru   Slacker   Uncensored   Unsloth   Zh
Model Card on HF 🤗: https://huggingface.co/hecan3d/QwenDGAF-2-4B 

QwenDGAF 2 4B Parameters and Internals

LLM NameQwenDGAF 2 4B
Repository 🤗https://huggingface.co/hecan3d/QwenDGAF-2-4B 
Base Model(s)  Qwen/Qwen3-4B   Qwen/Qwen3-4B
Model Size4b
Required VRAM1.8 GB
Updated2026-11-06
Maintainerhecan3d
Model Typeqwen3
Instruction-BasedYes
Model Files  8.1 GB   1.8 GB   2.1 GB   2.4 GB   2.5 GB   3.3 GB   4.3 GB
Supported Languagesru en zh
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.5.0
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to QwenDGAF 2 4B

Best Alternatives
Context / RAM
Downloads
Likes
Driptips Concierge Qwen3 4B256K / 8.1 GB600
...wen3 4B Toolcalling Gguf Codex256K / 4.3 GB261355
...B Toolcall Gguf Llamacpp Codex256K / 4.3 GB13049
...inecraftism 4B Uncensored GGUF256K / 2.1 GB6156
Qwen3 4B Pirate256K / 8.1 GB5571
...Instruct 2507 Unsloth Bnb 4bit256K / 3.5 GB15450417
Qwen3 4b Merged Txt256K / 8.1 GB5350
Qwen3 4B Instruct 2507 4bit256K / 2.3 GB4095511
...wen 3 4b Mythos Finetune 16bit256K / 8.1 GB920
Qwen3 4B INST Math256K / 8.1 GB220
Note: green Score (e.g. "73.2") means that the model is better than hecan3d/QwenDGAF-2-4B.