Stable GGUF models
120 GGUF models in the Stable family, quantized by 55 uploaders. Sizes run from 84M to 16.4B parameters. The longest trained context is 32K tokens.
About the Stable GGUF models
Stable is represented on ggufmodels.com by 120 GGUF models, quantized by 55 uploaders on Hugging Face. The most downloaded are stable diffusion v1 5, stable diffusion 3.5 large and stable diffusion 3.5 medium. Parameter counts run from 84M to 16.4B, and the longest trained context window is 32K tokens.
A Q4_K_M file of a Stable model is between 0.1 to 7.9 GB, which is the quant most people start with. Most files come from gpustack (14), mradermacher (10) and thepatch (8). The quants you will meet most often are Q8_0 (88), Q4_0 (63), Q4_K_M (51) and Q4_1 (47), where the number is how many models offer that quant.
Frequently asked questions
Which Stable GGUF should I download?
The most downloaded Stable GGUF here is stable diffusion v1 5. 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 Stable model need?
Q4_K_M files of Stable models on this site range from 0.1 to 7.9 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 Stable GGUF files come from?
The most common quantizers here are gpustack, mradermacher and thepatch. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.