sarvam translate needs about 5.8 GB of memory at Q8_0 (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.2 GB (Q6_K) to 7.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
sarvam translate is a 3.88B-parameter Sarvam model in GGUF format, quantized by spitfire4794. Its trained context length is 128K tokens. The repository has 3 quant files, from 3.2 GB (Q6_K) to 7.8 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q8_0 | 4.1 GB | 5.8 GB | Fits | Get file → | |
| F16 | 7.8 GB | 9.4 GB | Too big | Get file → |
What GPU do you need for sarvam translate?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (7.8 GB file, about 9.4 GB in use).
Which sarvam translate quant should you choose?
Q8_0 (4.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q6_K at 3.2 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about sarvam translate
How much VRAM does sarvam translate need?
About 5.8 GB at Q8_0 with an 8K context window. That is the 4.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run sarvam translate on an 8 GB GPU?
Yes, with Q8_0: the 4.1 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of sarvam translate GGUF?
It depends on the quant: Q6_K is 3.2 GB, Q8_0 is 4.1 GB, F16 is 7.8 GB.
What context length does sarvam translate support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download sarvam translate GGUF?
The files are on Hugging Face in the spitfire4794/sarvam-translate-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does sarvam translate use?
Hugging Face lists the license as gpl-3.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.