Bagel GGUF models
84 GGUF models in the Bagel family, quantized by 20 uploaders. Sizes run from 1.1B to 60.8B parameters. The longest trained context is 1024K tokens.
About the Bagel GGUF models
Bagel is represented on ggufmodels.com by 84 GGUF models, quantized by 20 uploaders on Hugging Face. The most downloaded are bagel 34b v0.5 i1, bagel dpo 34b v0.5 i1 and bagel dpo 20b v04 i1. Parameter counts run from 1.1B to 60.8B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Bagel model is between 0.7 to 36.7 GB, which is the quant most people start with. Most files come from mradermacher (36), RichardErkhov (8) and TheBloke (7). The quants you will meet most often are Q2_K (72), Q4_K_M (71), Q6_K (70) and Q3_K_M (69), where the number is how many models offer that quant.
Frequently asked questions
Which Bagel GGUF should I download?
The most downloaded Bagel GGUF here is bagel 34b v0.5 i1. 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 Bagel model need?
Q4_K_M files of Bagel models on this site range from 0.7 to 36.7 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 Bagel GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov and TheBloke. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.