SmolVLM 500M Base needs about 1.1 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 0.4 GB (Q6_K).
SmolVLM 500M Base – a compact vision‑language model
SmolVLM 500M Base is a 0.409 billion‑parameter vision‑language model based on the llama architecture. It supports 8192‑token context and is available in multiple GGUF quantizations. The model is hosted on the HuggingFace Hub and can be used with llama.cpp.
Good at
- Vision‑language inference
- Fast inference on low‑VRAM GPUs
- Small model footprint
Limits
- No license information provided
- No explicit vision support details
- Limited to 8192‑token context
Best for
- Quick prototyping of vision‑language tasks
- Running on 8 GB VRAM setups
- Low‑resource inference
Who it’s for. Developers and researchers needing a lightweight vision‑language model for experimentation or deployment on modest hardware. The model is suitable for those who can work with the provided GGUF files and do not require extensive licensing details.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.8 GB | Fits | Get file → | |
| IQ1_S | 0.2 GB | 1.1 GB | Fits | Get file → | |
| IQ1_M | 0.2 GB | 1.1 GB | Fits | Get file → | |
| IQ2_XXS | 0.2 GB | 1.1 GB | Fits | Get file → | |
| IQ2_XS | 0.2 GB | 1.1 GB | Fits | Get file → | |
| IQ2_S | 0.2 GB | 1.1 GB | Fits | Get file → | |
| IQ2_M | 0.2 GB | 1.1 GB | Fits | Get file → | |
| Q2_K_S | 0.2 GB | 1.1 GB | Fits | Get file → | |
| IQ3_XXS | 0.2 GB | 1.1 GB | Fits | Get file → | |
| IQ3_S | 0.2 GB | 1.1 GB | Fits | Get file → | |
| IQ3_XS | 0.2 GB | 1.1 GB | Fits | Get file → | |
| Q2_K | 0.2 GB | 1.1 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB | 1.1 GB | Fits | Get file → | |
| IQ3_M | 0.3 GB | 1.1 GB | Fits | Get file → | |
| IQ4_XS | 0.3 GB | 1.1 GB | Fits | Get file → | |
| IQ4_NL | 0.3 GB | 1.1 GB | Fits | Get file → | |
| Q4_0 | 0.3 GB | 1.1 GB | Fits | Get file → | |
| Q3_K_M | 0.3 GB | 1.1 GB | Fits | Get file → | |
| Q3_K_L | 0.3 GB | 1.1 GB | Fits | Get file → | |
| Q4_1 | 0.3 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_S | 0.3 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 1.2 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.2 GB | Fits | Get file → | |
| Q6_K | 0.4 GB | 1.3 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_K_M quant (0.3 GB file, ~1.1 GB RAM) is a good balance. If memory is tighter, use IQ1_S or IQ1_M (0.23 GB file, ~1.1 GB RAM). For the smallest footprint, Q2_K (0.25 GB file, ~1.1 GB RAM) is recommended. Estimates are approximate.
What GPU do you need for SmolVLM 500M Base?
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 (0.4 GB file, about 1.3 GB in use).
Which SmolVLM 500M Base quant should you choose?
Q4_K_M is the usual starting point for SmolVLM 500M Base: it balances file size and quality well. Here it is a 0.3 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SmolVLM 500M Base
How much VRAM does SmolVLM 500M Base need?
About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.3 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 500M Base on an 8 GB GPU?
Yes, with Q6_K: the 0.4 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SmolVLM 500M Base GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.2 GB, IQ1_M is 0.2 GB, IQ2_XXS is 0.2 GB, IQ2_XS is 0.2 GB, IQ2_S is 0.2 GB and 19 more.
What context length does SmolVLM 500M Base support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.
Where can I download SmolVLM 500M Base GGUF?
The files are on Hugging Face in the mradermacher/SmolVLM-500M-Base-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run SmolVLM 500M Base on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 1.1 GB RAM at 8k context, fitting within 8 GB VRAM with room for other processes.
Which quant gives the smallest file size?
IQ1_S, IQ1_M, and IQ2_XXS all have a file size of 0.23 GB, the smallest among the available quants.
Is there a license for this model?
No license information is provided in the supplied facts.