Tema GGUF models
75 GGUF models in the Tema family, quantized by 6 uploaders. Sizes run from 354M to 79.7B parameters. The longest trained context is 256K tokens.
About the Tema GGUF models
Tema is represented on ggufmodels.com by 75 GGUF models, quantized by 6 uploaders on Hugging Face. The most downloaded are Tema_Q R2.0 Code, Tema_Q X3 and Tema_Q X5 Thinking. Parameter counts run from 354M to 79.7B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Tema model is between 0.2 to 48.5 GB, which is the quant most people start with. Most files come from mradermacher (54), TaQuants (7) and yuna1126 (6). The quants you will meet most often are Q4_K_M (65), Q2_K (59), Q3_K_M (58) and Q6_K (57), where the number is how many models offer that quant.
Frequently asked questions
Which Tema GGUF should I download?
The most downloaded Tema GGUF here is Tema_Q R2.0 Code. 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 Tema model need?
Q4_K_M files of Tema models on this site range from 0.2 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 Tema GGUF files come from?
The most common quantizers here are mradermacher, TaQuants and yuna1126. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.