SmolVLM2 2.2B Instruct needs about 3.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.4 GB (IQ1_S) to 1.5 GB (Q6_K).
SmolVLM2 2.2B Instruct – lightweight multimodal model for video, image, and text
SmolVLM2 2.2B Instruct is a compact multimodal model that processes video, images, and text to generate text responses. It is based on the Idefics3 architecture and is licensed under Apache 2.0. The model is optimized for on‑device inference with limited GPU resources.
Good at
- Video and image analysis
- Text‑to‑image queries
- Multimodal captioning
Limits
- No image or video generation
- Requires 5.2GB GPU RAM for video inference
- No support for non‑English languages
Best for
- On‑device video captioning
- Visual question answering
- Multimodal storytelling
Who it’s for. Developers building lightweight multimodal applications that need to run on devices with limited GPU memory. Researchers requiring a small, vision‑enabled model for rapid prototyping.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.4 GB | 2.6 GB | Fits | Get file → | |
| IQ1_M | 0.5 GB | 2.6 GB | Fits | Get file → | |
| IQ2_XXS | 0.5 GB | 2.6 GB | Fits | Get file → | |
| IQ2_XS | 0.6 GB | 2.7 GB | Fits | Get file → | |
| IQ2_S | 0.6 GB | 2.7 GB | Fits | Get file → | |
| IQ2_M | 0.7 GB | 2.8 GB | Fits | Get file → | |
| Q2_K_S | 0.7 GB | 2.8 GB | Fits | Get file → | |
| Q2_K | 0.7 GB | 2.8 GB | Fits | Get file → | |
| IQ3_XXS | 0.7 GB | 2.8 GB | Fits | Get file → | |
| IQ3_XS | 0.8 GB | 2.9 GB | Fits | Get file → | |
| IQ3_S | 0.8 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_S | 0.8 GB | 2.9 GB | Fits | Get file → | |
| IQ3_M | 0.9 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 3.1 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 3.1 GB | Fits | Get file → | |
| IQ4_NL | 1.0 GB | 3.2 GB | Fits | Get file → | |
| Q4_0 | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q4_1 | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_S | 1.3 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 3.4 GB | Fits | Get file → | |
| Q6_K | 1.5 GB | 3.6 GB | Fits | Get file → |
For 8GB VRAM, use IQ1_S (0.45 GB) or IQ1_M (0.48 GB) – memory usage is about 2.6 GB at 8k context. If 12GB VRAM is available, Q4_K_M (1.11 GB) or Q5_K_M (1.3 GB) provide higher quality while staying under 4 GB memory. For the best trade‑off between size and quality, Q3_K_M (0.9 GB) is recommended.
What GPU do you need for SmolVLM2 2.2B Instruct?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q6_K (1.5 GB file, about 3.6 GB in use).
Which SmolVLM2 2.2B Instruct quant should you choose?
Q4_K_M is the usual starting point for SmolVLM2 2.2B Instruct: it balances file size and quality well. Here it is a 1.1 GB file.
If memory is tight, the smallest file is IQ1_S at 0.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SmolVLM2 2.2B Instruct
How much VRAM does SmolVLM2 2.2B Instruct need?
About 3.2 GB at Q4_K_M with an 8K context window. That is the 1.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run SmolVLM2 2.2B Instruct on an 8 GB GPU?
Yes, with Q6_K: the 1.5 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SmolVLM2 2.2B Instruct GGUF?
It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB, IQ2_M is 0.7 GB and 18 more.
What context length does SmolVLM2 2.2B Instruct support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.
Where can I download SmolVLM2 2.2B Instruct GGUF?
The files are on Hugging Face in the mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SmolVLM2 2.2B Instruct use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run SmolVLM2 2.2B Instruct on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations will keep VRAM usage around 2.6 GB at 8k context.
Does the model support image generation?
No, the model only performs analysis and text generation based on visual input.
What license applies to this model?
The model is released under the Apache 2.0 license.