InternVL2 2B — Hardware Requirements & GPU Compatibility
Vision
InternVL2-2B is OpenGVLab's 2.2-billion-parameter instruction-tuned vision-language model, part of the InternVL 2.0 family that ranges from 1 billion to 108 billion parameters. It pairs the InternViT-300M-448px vision encoder with the internlm2-chat-1.8b language model through an MLP projector, and is trained to handle document and chart comprehension, infographics QA, scene-text and OCR tasks, scientific and mathematical problem solving, and multi-image or video input. Compared with earlier Mini-InternVL models it adds support for long texts, multiple images, and video within the same training context. At just over 2 billion parameters, it runs comfortably on a single consumer GPU or even weaker hardware. Context length is 8,192 tokens, matching its 8k training context window. It is released under the MIT license, permitting unrestricted commercial and research use. It was published in June 2024, and has since been superseded by the InternVL2.5 and InternVL3 series.
710.5K downloads
82 likesSpecifications
- Publisher
- OpenGVLab
- Parameters
- 2.2B
- Architecture
- InternVLChatModel
- Release Date
- 2024-06-27
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does InternVL2 2B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 4.8 GB | — | 4.41 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run InternVL2 2B?
BF16 · 4.8 GBInternVL2 2B (BF16) requires 4.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run InternVL2 2B?
BF16 · 4.8 GB59 devices with unified memory can run InternVL2 2B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Apple iPhone 17 Pro.
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does InternVL2 2B need?
InternVL2 2B requires 4.8 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2.2B × 16 bits ÷ 8 = 4.4 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF164.8 GB- Can I run InternVL2 2B on a Mac?
InternVL2 2B requires at least 4.8 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run InternVL2 2B locally?
Yes — InternVL2 2B can run locally on consumer hardware. At BF16 quantization it needs 4.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is InternVL2 2B?
At BF16, InternVL2 2B can reach ~990 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~135 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 4.8 × 0.65 = ~1072 tok/s
Estimated speed at BF16 (4.8 GB)
~1072 tok/s~135 tok/s~1072 tok/s~990 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of InternVL2 2B?
At BF16, the download is about 4.41 GB.
- Which GPUs can run InternVL2 2B?
52 consumer GPUs can run InternVL2 2B at BF16 (4.8 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run InternVL2 2B?
59 devices with unified memory can run InternVL2 2B at BF16 (4.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.