Smolvlm GGUF models
116 GGUF models in the Smolvlm family, quantized by 61 uploaders. Sizes run from 163M to 7.62B parameters. The longest trained context is 125K tokens.
About the Smolvlm GGUF models
Smolvlm is represented on ggufmodels.com by 116 GGUF models, quantized by 61 uploaders on Hugging Face. The most downloaded are SmolVLM2 2.2B Instruct, SmolVLM 500M Instruct and SmolVLM2 500M Video Instruct. Parameter counts run from 163M to 7.62B, and the longest trained context window is 125K tokens.
A Q4_K_M file of a Smolvlm model is between 0.1 to 1.1 GB, which is the quant most people start with. Most files come from mradermacher (24), lewiswatson (6) and ggml-org (6). The quants you will meet most often are Q8_0 (73), Q4_K_M (66), F16 (47) and Q6_K (43), where the number is how many models offer that quant.
Frequently asked questions
Which Smolvlm GGUF should I download?
The most downloaded Smolvlm GGUF here is SmolVLM2 2.2B Instruct. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Smolvlm model need?
Q4_K_M files of Smolvlm models on this site range from 0.1 to 1.1 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Smolvlm GGUF files come from?
The most common quantizers here are mradermacher, lewiswatson and ggml-org. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.