Local LLM model page

InternVL3 (8B)

Shanghai AI Lab multimodal model. Strong vision understanding for documents, charts, and photos. MIT licensed. Note: primarily PyTorch/safetensors — community GGUF may vary.

Find the best model for my hardware Browse all 183 LLMs

Parameters

Minimum RAM

8 GB

Model size

5 GB

Quantization

Q4_K_M

Can InternVL3 (8B) run locally?

InternVL3 (8B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q4_K_M as the default quantization, with at least 8 GB RAM.

Search term for LM Studio or compatible runtimes: internvl3-8b

Hugging Face repository: OpenGVLab/InternVL3-8B-Instruct

visionstandard

Strengths

Excellent document understanding
Strong chart and graph reading
MIT licensed
Good balance of vision and language

Limitations

Not the best for general text-only tasks
8GB RAM needed
Slower than text-only models

Best use cases

Document analysis and OCR
Chart understanding
Photo description
Multimodal Q&A
Visual reasoning

Benchmarks

Speed: 7/10

Quality: 7/10

Coding: 5/10

Reasoning: 7/10

Technical details

Developer: Shanghai AI Lab (OpenGVLab)

License: MIT

Context window: 32,768 tokens

Architecture: Vision-Language Model with InternViT-6B vision encoder

Released: 2025-04