Coder GGUF models
130 GGUF models in the Coder family, quantized by 47 uploaders. Sizes run from 18M to 79B parameters. The longest trained context is 256K tokens.
About the Coder GGUF models
Coder is represented on ggufmodels.com by 130 GGUF models, quantized by 47 uploaders on Hugging Face. The most downloaded are Models 01 Ai Yi Coder 9B Chat, Models 01 Ai Yi Coder 1.5B Chat and Yi Coder 1.5B Chat. Parameter counts run from 18M to 79B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Coder model is between 0.0 to 48.5 GB, which is the quant most people start with. Most files come from mradermacher (45), RichardErkhov (7) and QuantFactory (6). The quants you will meet most often are Q4_K_M (108), Q6_K (85), Q5_K_M (84) and Q2_K (83), where the number is how many models offer that quant.
Frequently asked questions
Which Coder GGUF should I download?
The most downloaded Coder GGUF here is Models 01 Ai Yi Coder 9B Chat. 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 Coder model need?
Q4_K_M files of Coder models on this site range from 0.0 to 48.5 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 Coder GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov and QuantFactory. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.