InternVL3 5 1B — Hardware Requirements & GPU Compatibility
Vision
InternVL3.5-1B is OpenGVLab's 1.1-billion-parameter multimodal model, pairing a 0.3-billion-parameter vision encoder with a 0.8-billion-parameter language model. It is the smallest member of the InternVL3.5 family, which the card says uses a Cascade Reinforcement Learning framework, offline RL followed by online RL, to improve reasoning, and it is the version fine-tuned from the InternVL3_5-1B-MPO checkpoint. The card covers general multimodal, reasoning, text and agentic benchmarks. It is small enough to run on almost any consumer GPU, a laptop or a CPU once quantized. The card does not state a context length, so none is given here. It is released under the Apache 2.0 license, permitting commercial and research use. Published in August 2025, it is the smallest of a series running from 1B up to a 241B mixture-of-experts model, with 2B, 4B, 8B, 14B and 38B dense siblings in between.
30.4K downloads
30 likesSpecifications
- Publisher
- OpenGVLab
- Parameters
- 1.1B
- Architecture
- InternVLChatModel
- Release Date
- 2025-08-25
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does InternVL3 5 1B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 0.5 GB | — | 0.45 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 0.5 GB | — | 0.46 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 0.6 GB | — | 0.52 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 0.6 GB | — | 0.53 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 0.7 GB | — | 0.64 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 0.8 GB | — | 0.76 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 1.0 GB | — | 0.88 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 1.2 GB | — | 1.06 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run InternVL3 5 1B?
Q4_K_M · 0.7 GBInternVL3 5 1B (Q4_K_M) requires 0.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ 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 InternVL3 5 1B?
Q4_K_M · 0.7 GB59 devices with unified memory can run InternVL3 5 1B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download InternVL3 5 1B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does InternVL3 5 1B need?
InternVL3 5 1B requires 0.7 GB of VRAM at Q4_K_M, or 2.3 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.1B × 4.8 bits ÷ 8 = 0.6 GB
KV Cache + Overhead ≈ 0.1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M0.7 GB- What's the best quantization for InternVL3 5 1B?
For InternVL3 5 1B, Q4_K_M (0.7 GB) offers the best balance of quality and VRAM usage. Q4_K_L (0.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.3 GB.
VRAM requirement by quantization
IQ2_XXS0.3 GBIQ3_XS0.5 GBQ3_K_L0.6 GBQ4_K_M ★0.7 GBQ4_K_L0.7 GBBF162.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run InternVL3 5 1B on a Mac?
InternVL3 5 1B requires at least 0.3 GB at IQ2_XXS, 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 InternVL3 5 1B locally?
Yes — InternVL3 5 1B can run locally on consumer hardware. At Q4_K_M quantization it needs 0.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is InternVL3 5 1B?
At Q4_K_M, InternVL3 5 1B can reach ~6857 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~936 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 ÷ 0.7 × 0.65 = ~7429 tok/s
Estimated speed at Q4_K_M (0.7 GB)
~7429 tok/s~936 tok/s~7429 tok/s~6857 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of InternVL3 5 1B?
At Q4_K_M, the download is about 0.64 GB. The full-precision BF16 version is 2.12 GB. The smallest option (IQ2_XXS) is 0.29 GB.
- Which GPUs can run InternVL3 5 1B?
52 consumer GPUs can run InternVL3 5 1B at Q4_K_M (0.7 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 InternVL3 5 1B?
59 devices with unified memory can run InternVL3 5 1B at Q4_K_M (0.7 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.