SA

sarvam 30b compressed

SarvamGGUF by kmr-kishoreUpdated 2026-04-29
Download on Hugging Face
Parameters32.2B
Context128K
Layers—
Architectureexaone-moe
Smallest quant19.5 GB
Quick answer

sarvam 30b compressed needs about 22.4 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, so it fits on a 24 GB GPU.

sarvam 30b compressed is a 32.2B-parameter Sarvam model in GGUF format, quantized by kmr-kishore. Its trained context length is 128K tokens. The repository has 1 quant file, from 19.5 GB (Q4_K_M) to 19.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M19.5 GB 22.4 GB
Too big Get file →

What GPU do you need for sarvam 30b compressed?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (19.5 GB file, about 22.4 GB in use).

Which sarvam 30b compressed quant should you choose?

Q4_K_M is the usual starting point for sarvam 30b compressed: it balances file size and quality well. Here it is a 19.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureexaone-moe
Parameters32.2B
Trained context131,072 tokens

Source

Quantized bykmr-kishore
FamilySarvam
Licenseapache-2.0
Downloads (HF)0
Last updated2026-04-29

Frequently asked questions about sarvam 30b compressed

How much VRAM does sarvam 30b compressed need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.5 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 compressed on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of sarvam 30b compressed GGUF?

It depends on the quant: Q4_K_M is 19.5 GB.

What context length does sarvam 30b compressed support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download sarvam 30b compressed GGUF?

The files are on Hugging Face in the kmr-kishore/sarvam-30b-compressed-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 30b compressed 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 kmr-kishore

All by kmr-kishore →

More Sarvam models

All Sarvam →

Other medium models

All medium models →