InternVL3 8B — Hardware Requirements & GPU Compatibility
Vision
InternVL3-8B is OpenGVLab's roughly 7.9-billion-parameter vision-language model, pairing an InternViT-300M vision encoder with a Qwen2.5-7B language backbone in a ViT-MLP-LLM architecture. It handles general image and video understanding and document analysis, extending into tool use, GUI agent tasks, and 3D scene perception beyond typical captioning. It is comfortably runnable on a single mainstream-to-high-end consumer GPU once quantized. Its language backbone supports a 32,768 token context window. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in April 2025 as part of a 1B-to-78B InternVL3 family sharing the same vision encoder. Its key change versus InternVL2.5 is Native Multimodal Pre-Training, which trains vision and language jointly from the start instead of adapting a language-only model afterward.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~125 tok/s · 32K)Macs from 16 GB (Q4_K_M · ~27 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run InternVL3 8B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/unsloth/InternVL3-8B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 16.2 GB free · 16K context
Download: InternVL3-8B-Q4_K_M.gguf4.68 GBunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3080 Ti (12 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~113 tok/s
- generation speed
- Cost per 1M output tokens
- $0.30
- per 1M output tokens
How Much VRAM Does InternVL3 8B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.7 GB | 9.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~177 tok/s | |
| 3.8 GB | 9.3 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~172 tok/s | |
| 4.3 GB | 9.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~154 tok/s | |
| 4.4 GB | 9.9 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~150 tok/s | |
| 5.2 GB | 10.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~125 tok/s | |
| 6.2 GB | 11.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~105 tok/s | |
| 7.2 GB | 12.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~91 tok/s | |
| 8.7 GB | 14.2 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~75 tok/s |
Selected Q4_K_M
4-bit medium quantization7.8GBat 16K context
- Weights
- 4.6 GB
- KV cache
- 2.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 16.2 GB free · ~125 tok/s
≥50 tok/s needs ≥403 GB/s · RTX 5090 ~222, RTX 3090 Ti ~125
Which Hardware Can Run InternVL3 8B?
Q4_K_M · 5.2 GBInternVL3 8B (Q4_K_M) requires 5.2 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. 151 devices with unified memory can run InternVL3 8B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 0.2 GB free · up to 16K ctx
16 GPUs · 1 device family
RTX 3080~94Simulate output on RTX 3080RTX 2080 Ti~76Simulate output on RTX 2080 TiRTX 3070 Ti~76Simulate output on RTX 3070 TiOrin Nano~13Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 12.2 GB free · up to 32K ctx
1 GPU
RX 7900 XT~92Simulate output on RX 7900 XT32–40 GB
fits · 24.2 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~222Simulate output on RTX 5090M5 Max36 GB~62Simulate output on Mac Studio M5 Max (36 GB)M532 GB~21Simulate output on MacBook Air 13" M5 (32 GB)Orin~25Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~17Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
| Gemma 4 E4BGoogle | — | 5.6 GB | ~123 | same size |
| Phi Mini MoE InstructMicrosoft | — | 5.4 GB | ~239 | same size |
| Gemma 3n E4B ITGoogle | — | 7.7 GB | ~127 | same size |
Specifications
- Publisher
- OpenGVLab
- Parameters
- 7.9B
- Architecture
- InternVLChatModel
- Release Date
- 2025-04-10
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does InternVL3 8B need?
InternVL3 8B requires 5.2 GB of VRAM at Q4_K_M, or 17.5 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 7.9B × 4.8 bits ÷ 8 = 4.8 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
What's the best quantization for InternVL3 8B?
For InternVL3 8B, Q4_K_M (5.2 GB) offers the best balance of quality and VRAM usage. Q5_K_S (6.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 2.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run InternVL3 8B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run InternVL3 8B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run InternVL3 8B locally?
Yes — InternVL3 8B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is InternVL3 8B?
At Q4_K_M, InternVL3 8B can reach ~916 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~125 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 ÷ 5.24 × 0.65 = ~992 tok/s
Estimated speed at Q4_K_M (5.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of InternVL3 8B?
At Q4_K_M, the download is about 4.77 GB. The full-precision BF16 version is 15.89 GB. The smallest option (IQ2_XXS) is 2.18 GB.
Which GPUs can run InternVL3 8B?
52 consumer GPUs can run InternVL3 8B at Q4_K_M. 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 InternVL3 8B?
151 devices with unified memory can run InternVL3 8B at Q4_K_M (5.2 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.