SmolVLM 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 3 quants, from 1.1 GB (Q4_K_M) to 3.6 GB (F16).
SmolVLM Instruct – compact multimodal model for image and text tasks
SmolVLM Instruct is a 1.81‑billion‑parameter multimodal model that accepts arbitrary sequences of image and text inputs to produce text outputs. It is based on the SmolLM2 language model and uses a lightweight vision encoder. The model is released under the Apache‑2.0 license.
Good at
- Image captioning
- Visual question answering
- Multimodal storytelling
Limits
- No image generation
- Requires 8‑k context for estimates
- Limited to English language
Best for
- On‑device inference of image‑text queries
- Rapid multimodal prototyping
- Low‑memory visual QA
Who it’s for. Developers building lightweight multimodal applications that need to run on devices with limited VRAM. Researchers testing multimodal models without heavy GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q8_0 | 1.9 GB | 4.0 GB | Fits | Get file → | |
| F16 | 3.6 GB | 5.7 GB | Fits | Get file → |
For 8‑GB VRAM, use Q4_K_M (1.11 GB, ~3.2 GB memory at 8k context). For 12‑GB VRAM, Q8_0 (1.93 GB, ~4 GB memory). For 24‑GB VRAM, F16 (3.63 GB, ~5.7 GB memory). Estimates are approximate.
What GPU do you need for SmolVLM 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 Q8_0 (1.9 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.6 GB file, about 5.7 GB in use).
Which SmolVLM Instruct quant should you choose?
Q4_K_M is the usual starting point for SmolVLM Instruct: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SmolVLM Instruct
How much VRAM does SmolVLM 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 SmolVLM Instruct on an 8 GB GPU?
Yes, with F16: the 3.6 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SmolVLM Instruct GGUF?
It depends on the quant: Q4_K_M is 1.1 GB, Q8_0 is 1.9 GB, F16 is 3.6 GB.
What context length does SmolVLM Instruct support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.
Where can I download SmolVLM Instruct GGUF?
The files are on Hugging Face in the ggml-org/SmolVLM-Instruct-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 SmolVLM 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 SmolVLM Instruct on 8 GB VRAM?
Yes, the Q4_K_M quantized model is 1.11 GB and requires about 3.2 GB memory at 8k context, fitting within 8 GB VRAM.
Does SmolVLM Instruct support image generation?
No, the model does not support image generation, only image‑to‑text tasks.
What license applies to SmolVLM Instruct?
The model is released under the Apache‑2.0 license.