SA

Sarvam 105b

SarvamGGUF by limegreenpeper1Updated 2026-03-13
Download on Hugging Face
Parameters106B
Context128K
Layers32
Architecturedeepseek2
Smallest quant64.2 GB
Quick answer

Sarvam 105b needs about 65.3 GB of memory at Q4_K_M (a 64.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 64.2 GB (Q4_K_M) to 112.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Sarvam 105b is a 106B-parameter Sarvam model in GGUF format, quantized by limegreenpeper1. Its trained context length is 128K tokens. The repository has 2 quant files, from 64.2 GB (Q4_K_M) to 112.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M64.2 GB (14 parts) 65.3 GB
Too big Get file →
Q8_0112.7 GB (24 parts) 113.8 GB
Too big Get file →

What GPU do you need for Sarvam 105b?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Sarvam 105b quant should you choose?

Q4_K_M is the usual starting point for Sarvam 105b: it balances file size and quality well. Here it is a 64.2 GB file.

The Q8_0 file is 112.7 GB, about 1.8 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

Architecturedeepseek2
Parameters106B (approximate, mixture of experts)
Layers32
Trained context131,072 tokens
KV cache (fp16)68 KB per token

Source

Quantized bylimegreenpeper1
FamilySarvam
Licenseapache-2.0
Downloads (HF)100
Last updated2026-03-13

Frequently asked questions about Sarvam 105b

How much VRAM does Sarvam 105b need?

About 65.3 GB at Q4_K_M with an 8K context window. That is the 64.2 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 105b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 65.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sarvam 105b GGUF?

It depends on the quant: Q4_K_M is 64.2 GB, Q8_0 is 112.7 GB.

What context length does Sarvam 105b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download Sarvam 105b GGUF?

The files are on Hugging Face in the limegreenpeper1/sarvam-105B-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 105b 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 limegreenpeper1

All by limegreenpeper1 →

More Sarvam models

All Sarvam →

Other large models

All large models →