Darwin GGUF models
87 GGUF models in the Darwin family, quantized by 24 uploaders. Sizes run from 1.88B to 180B parameters. The longest trained context is 256K tokens.
About the Darwin GGUF models
Darwin is represented on ggufmodels.com by 87 GGUF models, quantized by 24 uploaders on Hugging Face. The most downloaded are POCKET 35B, POCKET-Darwin-180B and Darwin 27B RSI. Parameter counts run from 1.88B to 180B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Darwin model is between 1.3 to 21.4 GB, which is the quant most people start with. Most files come from mradermacher (52), FINAL-Bench (7) and bartowski (4). The quants you will meet most often are Q4_K_M (69), Q6_K (60), Q3_K_M (60) and Q2_K (60), where the number is how many models offer that quant.
Frequently asked questions
Which Darwin GGUF should I download?
The most downloaded Darwin GGUF here is POCKET 35B. 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 Darwin model need?
Q4_K_M files of Darwin models on this site range from 1.3 to 21.4 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 Darwin GGUF files come from?
The most common quantizers here are mradermacher, FINAL-Bench and bartowski. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.