Blossom GGUF models
120 GGUF models in the Blossom family, quantized by 10 uploaders. Sizes run from 3.09B to 40B parameters. The longest trained context is 512K tokens.
About the Blossom GGUF models
Blossom is represented on ggufmodels.com by 120 GGUF models, quantized by 10 uploaders on Hugging Face. The most downloaded are Blossom V6.2 8B, Blossom v3 Baichuan2 7b and Blossom V6.2 32B. Parameter counts run from 3.09B to 40B, and the longest trained context window is 512K tokens.
A Q4_K_M file of a Blossom model is between 1.9 to 24.0 GB, which is the quant most people start with. Most files come from mradermacher (75), Azure99 (24) and RichardErkhov (6). The quants you will meet most often are Q4_K_M (116), Q4_K_S (111), Q6_K (110) and Q5_K_S (110), where the number is how many models offer that quant.
Frequently asked questions
Which Blossom GGUF should I download?
The most downloaded Blossom GGUF here is Blossom V6.2 8B. 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 Blossom model need?
Q4_K_M files of Blossom models on this site range from 1.9 to 24.0 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 Blossom GGUF files come from?
The most common quantizers here are mradermacher, Azure99 and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.