Snowflake GGUF models
76 GGUF models in the Snowflake family, quantized by 35 uploaders. Sizes run from 23M to 479B parameters. The longest trained context is 8K tokens.
About the Snowflake GGUF models
Snowflake is represented on ggufmodels.com by 76 GGUF models, quantized by 35 uploaders on Hugging Face. The most downloaded are snowflake arctic embed m v1.5, Snowflake Arctic Embed L v2.0 and Snowflake Arctic Embed S. Parameter counts run from 23M to 479B, and the longest trained context window is 8K tokens.
A Q4_K_M file of a Snowflake model is between 0.0 to 0.4 GB, which is the quant most people start with. Most files come from mradermacher (13), yixuan-chia (11) and keisuke-miyako (7). The quants you will meet most often are Q8_0 (58), Q4_K_M (28), Q5_K_M (26) and F16 (26), where the number is how many models offer that quant.
Frequently asked questions
Which Snowflake GGUF should I download?
The most downloaded Snowflake GGUF here is snowflake arctic embed m 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 Snowflake model need?
Q4_K_M files of Snowflake models on this site range from 0.0 to 0.4 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 Snowflake GGUF files come from?
The most common quantizers here are mradermacher, yixuan-chia and keisuke-miyako. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.