LLM EXPLORER 57,252 MODELS INDEXED

Qwen3 VL 2B Instruct FP8 by Qwen

By Qwen · 65063 downloads
HF Repo ↗ Copy URL

Qwen3 VL 2B Instruct FP8 is an open-source language model by Qwen. Features: 2b LLM, VRAM: 3.5GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.28.

  Arxiv:2308.12966   Arxiv:2409.12191   Arxiv:2502.13923   Arxiv:2505.09388 Base model:quantized:qwen/qwen... Base model:qwen/qwen3-vl-2b-in...   Conversational   Deploy:azure   Endpoints compatible   Fp8   Image-text-to-text   Instruct   Qwen3 vl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct-FP8 

Qwen3 VL 2B Instruct FP8 Parameters and Internals

LLM NameQwen3 VL 2B Instruct FP8
Repository 🤗https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct-FP8 
Base Model(s)  Qwen/Qwen3-VL-2B-Instruct   Qwen/Qwen3-VL-2B-Instruct
Model Size2b
Required VRAM3.5 GB
Updated2026-08-08
MaintainerQwen
Model Typeqwen3_vl
Instruction-BasedYes
Model Files  3.5 GB: 1-of-1
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3 VL 2B Instruct FP8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen 3 VL 2B Instruct Heretic0K / 4.3 GB442
Typhoon Ocr1.5 2B0K / 4.3 GB5502925
SingGuard 2B0K / 4.3 GB7477
ZwZ 2B0K / 4.9 GB585
...L 2B Instruct Unsloth Bnb 4bit0K / 2.4 GB1648448
...i Qwen3 VL 2B Instruct Ab 4bit0K / 1.8 GB1441
Qwen3 VL 2B Instruct 4bit0K / 1.8 GB18812
...en3 VL 2B Instruct Abliterated0K / 4.3 GB103021
Qwen3 VL 2B Instruct 8bit0K / 2.6 GB761
Qwen3 VL 2B Instruct 6bit0K / 2.2 GB361
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-VL-2B-Instruct-FP8.