Translategemma GGUF models
90 GGUF models in the Translategemma family, quantized by 53 uploaders. Sizes run from 60M to 27B parameters. The longest trained context is 128K tokens.
About the Translategemma GGUF models
Translategemma is represented on ggufmodels.com by 90 GGUF models, quantized by 53 uploaders on Hugging Face. The most downloaded are Translategemma 4b It, Translategemma 12b It and Translategemma 4b It. Parameter counts run from 60M to 27B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Translategemma model is between 2.5 to 16.5 GB, which is the quant most people start with. Most files come from mradermacher (9), NikolayKozloff (7) and u3man (4). The quants you will meet most often are Q4_K_M (53), Q8_0 (31), Q6_K (27) and Q5_K_M (27), where the number is how many models offer that quant.
Frequently asked questions
Which Translategemma GGUF should I download?
The most downloaded Translategemma GGUF here is Translategemma 4b It. 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 Translategemma model need?
Q4_K_M files of Translategemma models on this site range from 2.5 to 16.5 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 Translategemma GGUF files come from?
The most common quantizers here are mradermacher, NikolayKozloff and u3man. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.