Nanbeige GGUF models
210 GGUF models in the Nanbeige family, quantized by 108 uploaders. Sizes run from 848M to 33.1B parameters. The longest trained context is 512K tokens.
About the Nanbeige GGUF models
Nanbeige is represented on ggufmodels.com by 210 GGUF models, quantized by 108 uploaders on Hugging Face. The most downloaded are Nanbeige4.3 33B, Nanbeige4.3-33B and Nanbeige4.3 33B UNCENSORED. Parameter counts run from 848M to 33.1B, and the longest trained context window is 512K tokens.
A Q4_K_M file of a Nanbeige model is between 0.5 to 21.2 GB, which is the quant most people start with. Most files come from mradermacher (58), NikolayKozloff (8) and enacimie (4). The quants you will meet most often are Q4_K_M (140), Q6_K (116), Q8_0 (113) and Q5_K_M (111), where the number is how many models offer that quant.
Frequently asked questions
Which Nanbeige GGUF should I download?
The most downloaded Nanbeige GGUF here is Nanbeige4.3 33B. 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 Nanbeige model need?
Q4_K_M files of Nanbeige models on this site range from 0.5 to 21.2 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 Nanbeige GGUF files come from?
The most common quantizers here are mradermacher, NikolayKozloff and enacimie. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.