Tulu GGUF models
104 GGUF models in the Tulu family, quantized by 15 uploaders. Sizes run from 268M to 69B parameters. The longest trained context is 128K tokens.
About the Tulu GGUF models
Tulu is represented on ggufmodels.com by 104 GGUF models, quantized by 15 uploaders on Hugging Face. The most downloaded are Tulu 2 7B Helpful, Tulu2 7b_writing Prompts and tulu 2 70b i1. Parameter counts run from 268M to 69B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Tulu model is between 0.4 to 41.4 GB, which is the quant most people start with. Most files come from mradermacher (71), TheBloke (9) and RichardErkhov (7). The quants you will meet most often are Q2_K (97), Q5_K_M (96), Q4_K_M (96) and Q3_K_M (95), where the number is how many models offer that quant.
Frequently asked questions
Which Tulu GGUF should I download?
The most downloaded Tulu GGUF here is Tulu 2 7B Helpful. 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 Tulu model need?
Q4_K_M files of Tulu models on this site range from 0.4 to 41.4 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 Tulu GGUF files come from?
The most common quantizers here are mradermacher, TheBloke and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.