SA

Sarvam 30b Full

SarvamGGUF by shiva1294Updated 2026-09-05
Download on Hugging Face
Parameters32.2B
Context128K
Layers19
Architecturebailingmoe2
Smallest quant19.6 GB
Quick answer

Sarvam 30b Full needs about 20.2 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 19.6 GB (Q4_K_M) to 34.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.

Sarvam 30b Full is a 32.2B-parameter Sarvam model in GGUF format, quantized by shiva1294. Its trained context length is 128K tokens. The repository has 2 quant files, from 19.6 GB (Q4_K_M) to 34.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M19.6 GB 20.2 GB
Too big Get file →
Q8_034.2 GB 34.9 GB
Too big Get file →

What GPU do you need for Sarvam 30b Full?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.6 GB file, about 20.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (19.6 GB file, about 20.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.2 GB file, about 34.9 GB in use).

Which Sarvam 30b Full quant should you choose?

Q4_K_M is the usual starting point for Sarvam 30b Full: it balances file size and quality well. Here it is a 19.6 GB file.

The Q8_0 file is 34.2 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebailingmoe2
Parameters32.2B (approximate, mixture of experts)
Layers19
Trained context131,072 tokens
KV cache (fp16)19 KB per token

Source

Quantized byshiva1294
FamilySarvam
Licenseapache-2.0
Downloads (HF)151
Last updated2026-09-05

Frequently asked questions about Sarvam 30b Full

How much VRAM does Sarvam 30b Full need?

About 20.2 GB at Q4_K_M with an 8K context window. That is the 19.6 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 30b Full on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sarvam 30b Full GGUF?

It depends on the quant: Q4_K_M is 19.6 GB, Q8_0 is 34.2 GB.

What context length does Sarvam 30b Full support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.6 GB at 32K.

Where can I download Sarvam 30b Full GGUF?

The files are on Hugging Face in the shiva1294/Sarvam-30B 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 30b Full use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from shiva1294

All by shiva1294 →

More Sarvam models

All Sarvam →

Other medium models

All medium models →