Stheno GGUF models
127 GGUF models in the Stheno family, quantized by 45 uploaders. Sizes run from 8B to 49.5B parameters. The longest trained context is 128K tokens.
About the Stheno GGUF models
Stheno is represented on ggufmodels.com by 127 GGUF models, quantized by 45 uploaders on Hugging Face. The most downloaded are L3-8B-Stheno-v3.2, L3-8B-Stheno-v3.2 and L3 8B Stheno v3.2. Parameter counts run from 8B to 49.5B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Stheno model is between 4.9 to 29.8 GB, which is the quant most people start with. Most files come from mradermacher (49), matrixportalx (6) and jsfs11 (6). The quants you will meet most often are Q4_K_M (98), Q5_K_M (88), Q6_K (87) and Q4_K_S (86), where the number is how many models offer that quant.
Frequently asked questions
Which Stheno GGUF should I download?
The most downloaded Stheno GGUF here is L3-8B-Stheno-v3.2. 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 Stheno model need?
Q4_K_M files of Stheno models on this site range from 4.9 to 29.8 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 Stheno GGUF files come from?
The most common quantizers here are mradermacher, matrixportalx and jsfs11. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.