SA

Sarvam 2b v0.5

SarvamGGUF by mradermacherUpdated 2025-12-01
Download on Hugging Face
Parameters2.51B
Context8K
Layers28
Architecturellama
Smallest quant1.0 GB
Quick answer

Sarvam 2b v0.5 needs about 3.0 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 1.0 GB (Q2_K) to 5.0 GB (F16).

Sarvam 2b v0.5 – a 2.51 billion‑parameter Llama model for Indic and English text

Sarvam 2b v0.5 is a 2.51 billion‑parameter Llama model trained from scratch on 2 trillion tokens. It supports ten Indic languages and English. The model is available in multiple GGUF quantizations for efficient inference.

Good at

  • Indic language text generation
  • English text completion
  • Multilingual support

Limits

  • No vision support
  • License is other
  • No post‑training fine‑tuning yet

Best for

  • Chatbots in Indian languages
  • Content creation in Hindi and Tamil
  • Educational tools for multilingual learners

Who it’s for. Developers building multilingual language applications who need a compact model with strong Indic language performance. Researchers interested in Llama‑based models for Indian languages may also find this checkpoint useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 2.4 GB
Fits Get file →
IQ3_XS1.1 GB 2.5 GB
Fits Get file →
IQ3_S1.1 GB 2.6 GB
Fits Get file →
Q3_K_S1.1 GB 2.6 GB
Fits Get file →
IQ3_M1.2 GB 2.6 GB
Fits Get file →
Q3_K_M1.2 GB 2.7 GB
Fits Get file →
Q3_K_L1.3 GB 2.8 GB
Fits Get file →
IQ4_XS1.4 GB 2.8 GB
Fits Get file →
Q4_K_S1.5 GB 2.9 GB
Fits Get file →
Q4_K_M1.5 GB 3.0 GB
Fits Get file →
Q5_K_S1.7 GB 3.2 GB
Fits Get file →
Q5_K_M1.8 GB 3.2 GB
Fits Get file →
Q6_K2.1 GB 3.5 GB
Fits Get file →
Q8_02.7 GB 4.1 GB
Fits Get file →
F165.0 GB 6.5 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.54 GB, estimated memory 3 GB). For 12 GB VRAM, Q5_K_M (1.79 GB, 3.2 GB) or Q6_K (2.06 GB, 3.5 GB). Larger VRAM allows Q8_0 (2.67 GB, 4.1 GB) or F16 (5.02 GB, 6.5 GB).

What GPU do you need for Sarvam 2b v0.5?

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: the best quant that fits is Q6_K (2.1 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.0 GB file, about 6.5 GB in use).

Which Sarvam 2b v0.5 quant should you choose?

Q4_K_M is the usual starting point for Sarvam 2b v0.5: it balances file size and quality well. Here it is a 1.5 GB file.

The Q8_0 file is 2.7 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.

If memory is tight, the smallest file is Q2_K at 1.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.51B
Layers28
Trained context8,192 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilySarvam
Licenseother
Downloads (HF)859
Last updated2025-12-01

Frequently asked questions about Sarvam 2b v0.5

How much VRAM does Sarvam 2b v0.5 need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 1.5 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 2b v0.5 on an 8 GB GPU?

Yes, with F16: the 5.0 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sarvam 2b v0.5 GGUF?

It depends on the quant: Q2_K is 1.0 GB, IQ3_XS is 1.1 GB, IQ3_S is 1.1 GB, Q3_K_S is 1.1 GB, IQ3_M is 1.2 GB, Q3_K_M is 1.2 GB and 9 more.

What context length does Sarvam 2b v0.5 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.9 GB at 8K.

Where can I download Sarvam 2b v0.5 GGUF?

The files are on Hugging Face in the mradermacher/sarvam-2b-v0.5-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 2b v0.5 use?

Hugging Face lists the license as other. 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 2b v0.5 on 8 GB VRAM?

Yes, use the Q4_K_M quant which requires about 3 GB of VRAM at 8 k context.

Does this model support image input?

No, Sarvam 2b v0.5 does not have vision capabilities.

What languages can it generate?

It supports Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, Telugu, and English.

Other GGUFs of sarvam-1-v0.5

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sarvam models

All Sarvam →

Other tiny models

All tiny models →