LLM EXPLORER 65,999 MODELS INDEXED

Qwen2.5 VL 3B Instruct GPTQ Safetensors by simaai

By simaai · 38 downloads
HF Repo ↗ Copy URL

Qwen2.5 VL 3B Instruct GPTQ Safetensors is an open-source language model by simaai. Features: 3b LLM, VRAM: 2.9GB, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.24.

Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-vl-3b-...   Compressed-tensors   Conversational   Endpoints compatible   Gptq   Image-text-to-text   Instruct   Multilingual   Quantized   Qwen2 5 vl   Region:us   Safetensors   Sima-ai
Model Card on HF 🤗: https://huggingface.co/simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors 

Qwen2.5 VL 3B Instruct GPTQ Safetensors Parameters and Internals

LLM NameQwen2.5 VL 3B Instruct GPTQ Safetensors
Repository 🤗https://huggingface.co/simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors 
Base Model(s)  Qwen/Qwen2.5-VL-3B-Instruct   Qwen/Qwen2.5-VL-3B-Instruct
Model Size3b
Required VRAM2.9 GB
Updated2026-10-22
Maintainersimaai
Model Typeqwen2_5_vl
Instruction-BasedYes
Model Files  2.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2_5_VLForConditionalGeneration
Licenseother
Model Max Length131072
Transformers Version5.10.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen2.5 VL 3B Instruct GPTQ Safetensors

Best Alternatives
Context / RAM
Downloads
Likes
Nanonets OCR2 3B 8bit125K / 4.6 GB1031
...L 3B Instruct Unsloth Bnb 4bit125K / 3.8 GB532316
...wen2.5 VL 3B Instruct Bnb 4bit125K / 2.5 GB43635
Qwen2.5 VL 3B Instruct 4bit125K / 3.1 GB32355
Holo1 3B 4bit125K / 3.1 GB271
Holo1 3B 3bit125K / 2.7 GB211
Qwen2.5 VL 3B Instruct 8bit125K / 4.1 GB5287
Qwen2.5 VL 3B Instruct 3bit125K / 2.7 GB2212
Qwen2.5 VL 3B Instruct 6bit125K / 3.2 GB983
Nanonets OCR2 3B125K / 7.5 GB659329511
Note: green Score (e.g. "73.2") means that the model is better than simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors.