SA

Sarvam 30b

SarvamGGUF by sarvamaiUpdated 2026-03-23
Download on Hugging Face
Parameters32.2B
Context128K
Layers19
Architecturebailingmoe2
Smallest quant19.6 GB
Quick answer

Sarvam 30b 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. Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.

Sarvam 30B – a 32.2B parameter Mixture‑of‑Experts model

Sarvam 30B is a 32.2B parameter MoE model built for practical deployment. It offers strong reasoning, reliable coding, and conversational quality across Indian languages. The model is open‑source under Apache‑2.0.

Good at

  • Reasoning and coding
  • Conversational quality in Indian languages
  • Long‑context stability with 131072 token context

Limits

  • Requires 19.57 GB GGUF file
  • Estimated 20.2 GB VRAM at 8K context
  • No vision support

Best for

  • Multilingual chat in Indian languages
  • Tool‑call enabled voice interactions
  • Resource‑constrained inference

Who it’s for. Developers and researchers needing a large‑scale MoE model that runs efficiently on limited hardware. The model is suitable for applications requiring robust reasoning and coding in Indian languages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M19.6 GB (6 parts) 20.2 GB
Too big Get file →

The only available quant is Q4_K_M, 19.57 GB. It needs about 20.2 GB VRAM at 8K context. For 8 GB VRAM, the model cannot run. If a larger GPU is available, use Q4_K_M for best performance.

What GPU do you need for Sarvam 30b?

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).

Which Sarvam 30b quant should you choose?

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

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 bysarvamai
FamilySarvam
Licenseapache-2.0
Downloads (HF)1,250
Last updated2026-03-23

Frequently asked questions about Sarvam 30b

How much VRAM does Sarvam 30b 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 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 GGUF?

It depends on the quant: Q4_K_M is 19.6 GB.

What context length does Sarvam 30b 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 GGUF?

The files are on Hugging Face in the sarvamai/sarvam-30b-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 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.

Can I run Sarvam 30B on 8 GB VRAM?

No, the Q4_K_M quant requires about 20.2 GB VRAM at 8K context, which exceeds 8 GB.

Does Sarvam 30B support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from sarvamai

All by sarvamai →

More Sarvam models

All Sarvam →

Other medium models

All medium models →