Stablelm GGUF models
117 GGUF models in the Stablelm family, quantized by 46 uploaders. Sizes run from 1.64B to 12.1B parameters. The longest trained context is 4K tokens.
About the Stablelm GGUF models
Stablelm is represented on ggufmodels.com by 117 GGUF models, quantized by 46 uploaders on Hugging Face. The most downloaded are stablelm 2 zephyr 1 6b, stablelm tuned alpha 7b i1 and stablelm zephyr 3b. Parameter counts run from 1.64B to 12.1B, and the longest trained context window is 4K tokens.
A Q4_K_M file of a Stablelm model is between 1.0 to 7.4 GB, which is the quant most people start with. Most files come from mradermacher (26), RichardErkhov (13) and tensorblock (5). The quants you will meet most often are Q4_K_M (71), Q5_K_M (70), Q6_K (62) and Q3_K_M (62), where the number is how many models offer that quant.
Frequently asked questions
Which Stablelm GGUF should I download?
The most downloaded Stablelm GGUF here is stablelm 2 zephyr 1 6b. 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 Stablelm model need?
Q4_K_M files of Stablelm models on this site range from 1.0 to 7.4 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 Stablelm GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.