Skip to content

Indian AI models: Sarvam 105B, Param2 and the GPUs to run them in India

19 November 2026Vinod Chacko
Indian AI models: Sarvam 105B, Param2 and the GPUs to run them in India

Part of our AI models guide: 11 posts on choosing and running AI models.

India's own AI models have reached the point where a business can download one and use it for free. Sarvam AI's Sarvam 30B and Sarvam 105B are open weights under Apache 2.0, which allows commercial use; BharatGen's Param2 17B carries a non-commercial licence. All three are built for India's 22 scheduled languages, but on Artificial Analysis's independent index (April 2026, an earlier index version) Sarvam 105B still trails OpenAI's open gpt-oss-120B. By our estimate, Sarvam 105B runs on one 8-GPU H100, H200 or B200 server at full precision, and its compressed 8-bit (FP8) version fits on a single H200 or B200 GPU. Indian-language text can need several times as many tokens as English on older tokenizers, which raises API bills, and payment and government data must stay in India: a strong case for running these models on GPUs in India.

India's AI models at a glance

India now has a handful of open-weight models built for Indian languages: Sarvam AI, a startup, leads, and BharatGen, a programme led by IIT Bombay, is second. Open weights means you can download a model and run it on your own GPUs (see open-weight vs closed models). Size is counted in parameters, the numbers a model learned in training. Sarvam 30B, Sarvam 105B and Param2 are mixture-of-experts (MoE) models: only some parameters, the active ones, work on each token (the smallest unit of text an AI model reads and writes, often a short word or part of one), so they cost less to run than their size suggests. Context is how much text, in tokens, the model reads at once.

Model

Released

Size (total, active)

Languages

Licence

Notes

Sarvam-1

Oct 2024

About 2.5B (named 2B)

10 Indian languages and English

Sarvam non-commercial

Sarvam's first small model

Sarvam-M

May 2025

24B

Indian languages and English

Apache 2.0

Built on Mistral Small 3.1, a French open model

Sarvam 30B

Feb 2026; weights 6 Mar 2026

32B total, 2.4B active

22 scheduled Indian languages and English

Apache 2.0

Trained from scratch in India on IndiaAI compute (Sarvam's account)

Sarvam 105B

Feb 2026; weights 6 Mar 2026

106B total, 10.3B active; 128K context

As Sarvam 30B

Apache 2.0

As Sarvam 30B

Prism (Sarvam AI)

3 Nov 2026

Built on Sarvam 105B

As Sarvam 105B

Apache 2.0

“Decision” model: picks from options you supply; writes no text

Sarvam-105B-1711

15 Nov 2026

As Sarvam 105B

As Sarvam 105B

Apache 2.0

More training for tool use, agents and Indian languages; FP4 and BF16 builds

Param2 17B (BharatGen)

Feb 2026

17B total, 2.4B active; 32K context

English, Hindi and 21 more Indian languages

BharatGen non-commercial

Built from scratch in India (BharatGen's account)

Sarvam weighted training towards the 10 most-spoken languages, so test yours.

What GPU Sarvam and Param2 need

Three rules size any model (our GPU memory guide has the maths):

  • Fit. The weights (a model's learned numbers) must fit in GPU memory: parameters times bytes per parameter. Full precision (BF16) uses 2 bytes, FP8 1 and FP4 about half a byte; lower precision shrinks the model with a small loss of quality.
  • Headroom. Our rule of thumb: keep the weights to about 80% of GPU memory, leaving the rest for the KV cache (the model's working memory per conversation); long contexts and many users need more.
  • MoE. Total size sets the memory and active size sets the speed. All 106B parameters of Sarvam 105B must sit in memory, though only 10.3B work on each token.

Model and precision

Weights

Smallest GPU count that holds it (sizing only)

Production setup

Sarvam 105B, BF16

About 212 GB

4 x H100 80 GB (Sarvam's example splits it across four GPUs)

One 8-GPU H100, H200 or B200 server

Sarvam 105B, FP8

About 106 GB

1 x H200 (141 GB) or B200 (180 GB)

8-GPU H200 or B200 server; B300 (2.3 TB per server) for many users or long chats

Sarvam-105B-1711, FP4

About 70 GB (download size)

1 x B200 or B300 (of the GPUs we source, only B200 and B300 run FP4 natively)

8-GPU B200 or B300 server

Prism, FP8

About 106 GB

1 x H200 or B200 (needs about 120 GB free, says Sarvam)

8-GPU H200 or B200 server; Sarvam reports a 44 ms median reply on one B200 (vendor-reported)

Sarvam 30B, BF16

About 64 GB

1 x H200

Several copies on one 8-GPU server

Sarvam 30B, FP8

About 32 GB

1 x H100

Several copies on one 8-GPU server

Param2 17B, BF16

About 34 GB

1 x H100

Shares an 8-GPU server with other models

These are our estimates, for sizing only: we source whole 8-GPU servers, and GPU counts on the model cards are examples, not minimums. One 8-GPU server can run several copies of Sarvam 30B or 105B, or an Indian model alongside a global one. Fine-tuning (further training on your own data) with LoRA, which trains small add-on layers instead of the whole model, fits on one 8-GPU server for Sarvam 30B or 105B. A full fine-tune needs roughly 16 bytes per parameter, about 1.7 TB for Sarvam 105B plus working memory, so plan a cluster of several 8-GPU servers or one B300 server with careful setup. See multi-server B300 clusters and B300 fine-tuning costs, or compare the B300 and B200 for many users.

How good are Indian models?

Built for Indian languages, still behind global open models on independent tests. Artificial Analysis, an independent benchmarking firm, scored Sarvam's models on its Intelligence Index (mostly English tasks, reasoning mode):

Artificial Analysis Intelligence Index v4 (published 2 Apr 2026)

Maker

Score

gpt-oss-120B (high reasoning setting)

OpenAI, US

33

GLM-4.5-Air

Zhipu AI (Z.ai), China

23

Qwen3 30B A3B 2507

Alibaba, China

22

Sarvam 105B

Sarvam AI, India

18

Sarvam 30B

Sarvam AI, India

12

Sarvam-M

Sarvam AI, India

8

These are version 4 scores. Artificial Analysis moved to version 5 on 27 October 2026 and shows no v5 score for Sarvam 105B, so do not compare them with v5 scores, including those elsewhere in this series. Sarvam's own tests (vendor-reported) tell a similar story:

Test (what it measures)

Sarvam 105B

Comparison in Sarvam's table

Reading

MMLU (general knowledge, English)

90.6

gpt-oss-120B: 90.0

Roughly level

SWE-Bench Verified (fixing real code)

45.0

gpt-oss-120B: 50.6; GLM-4.5-Air: 57.6

Behind

Arena Hard v2 (hard chat prompts)

71.0

gpt-oss-120B: 88.5

Behind

Indian-language win rate (110 prompts in 22 languages, Gemini 3 as judge)

90% average (Sarvam 30B: 89%)

Opposing models not named

Strong claim, not independently checked

We found no independent leaderboard for Indian-language text yet. Early software gaps are closed: vLLM, the popular serving software, has supported Sarvam 30B and 105B natively since 7 March 2026, and official compressed builds (FP8 for servers, GGUF for small machines) followed later that month.

Our advice:

  • Indian-language chat, search and voice front ends: an Indian model.
  • Code and multi-step reasoning: a global open model.
  • Before you choose: test 100 of your own prompts in your own languages.

Why Indian languages cost more per word

APIs charge per token, and a GPU produces a fixed number of tokens a second (our token pricing guide explains the billing). Each model's tokenizer decides how text is cut into tokens, and many cut Indian scripts into far more pieces than English. A July 2026 preprint, "The Tokenizer Tax", counted tokens per word on the same professionally translated sentences (FLORES-200):

Tokens per word vs English (English = 1.00)

GPT-4 tokenizer

GPT-4o tokenizer

Qwen2.5 tokenizer

Hindi

4.08

1.34

3.79

Marathi

5.84

2.11

5.33

Bengali

6.52

1.91

5.65

Gujarati

8.00

1.87

7.03

Tamil

9.89

2.57

7.92

Telugu

10.68

2.49

9.02

Kannada

12.06

2.72

9.42

Malayalam

13.04

2.85

10.54

Per-word ratios are a different measure from the totals in our token pricing guide, which count every token in whole sentences. On that basis, GPT-4's tokenizer needed about 4.8 times as many tokens as English for Hindi and 9 times for Malayalam; use totals like these, not per-word ratios, to estimate cost. The gap is a design choice: across Indian languages, GPT-4o's tokenizer needs on average about 73% fewer tokens per word than GPT-4's. Sarvam says the tokenizer it built for Sarvam-1 in 2024 needs 1.4 to 2.1 tokens per word in 10 Indian languages, against about 1.4 for English (vendor-reported).

On an API, more tokens means a bigger bill; on your own server, fewer answers per GPU-hour. Before you budget, count tokens on your own prompts with each candidate model's tokenizer.

IndiaAI GPU rates and who can apply

The government buys GPU time from empanelled providers and offers it to eligible Indian users at subsidised rates through the IndiaAI compute portal. If you qualify, apply.

Item

Figure

Source and date

Approved

₹10,371.92 crore (a crore is 10 million rupees) over five years; a target of 10,000 or more GPUs through public-private partnership

Union Cabinet, 7 Mar 2024

Portal opened

Up to 40% subsidy for eligible users; about 14,000 GPUs live at launch

MeitY launch, 6 Mar 2025

GPUs

38,231 onboarded; IndiaAI's empanelment list shows 44,077 accelerators offered by 13 bidders (offered, not necessarily live)

Lok Sabha answer, 25 Mar 2026; IndiaAI list dated 3 Nov 2026

Home-grown models backed

20 proposals: 12 large models and 8 small ones

Parliament answers, Jul and Aug 2026

Where the subsidy has gone

₹1,058 crore of ₹1,275 crore committed (about 83%) to nine foundation-model builders; ₹10.14 crore (0.8%) to researchers, students and fellows

ThePrint, portal data to 8 Oct 2026

That split follows the design: building India's own foundation models is a main aim, and the government has paid about 99% of those builders' bills so far (ThePrint). Sarvam, for one, was allocated 4,096 H100s for six months in 2025, and its ₹246.72 crore bill is fully subsidised.

Who can apply: startups and MSMEs working in AI that have DPIIT recognition, ₹50 lakh of annual revenue or ₹1 crore of funding; researchers meeting citation thresholds; students, IndiaAI fellows and government bodies. Requests go in from the 1st to the 25th of each month; those under 5,000 GPU-hours are approved automatically, and larger ones go to a committee.

Reference on-demand rates (13 Mar 2026), eligible users only

Per hour, whole 8-GPU server

Per GPU-hour

H100 SXM

₹1,224

₹153 (about US$1.61)

H200 SXM

₹1,125

₹140.63 (about US$1.48)

B200 SXM

₹2,584

₹323 (about US$3.39)

A100 80GB

₹1,087.20

₹135.90 (about US$1.43)

IndiaAI calls these indicative and does not say whether they are before or after the subsidy; they are not market prices. GPU businesses can read how they shape the market in our guide for GPU clouds in India.

API, IndiaAI or your own GPUs?

The break-even between paying per token and running your own server is in our LLM sizing guide and rent, buy or API guide.

Route

Good fit when

Watch out for

Sarvam's own API (prices below)

Low or spiky volume; quick pilots

Introductory prices end with 2026; prompts go to a third party; Sarvam 30B is marked for retirement there

IndiaAI compute portal

You are an eligible Indian startup, researcher or public body

Monthly approval cycle; large requests go to a committee

Your own dedicated 8-GPU server in India

Steady volume; fine-tuning on company data; data that must stay in India; real-time voice

Whole 8-GPU servers, terms of a year or more, billed upfront; costs the same busy or idle; you run the serving software (vLLM or SGLang)

Sarvam's API prices, before GST: Sarvam 105B costs ₹10 per million input tokens (₹0.25 cached) and ₹25 per million output tokens; Prism costs ₹4 per million input tokens, with no output charge. OpenRouter, a marketplace for many models' APIs, listed no model from an Indian lab when we checked on 19 November 2026.

Why run Indian models in India

India has no blanket rule that data must stay in the country, but sector rules point regulated buyers there. Payment system data must be stored only in India (Reserve Bank of India, since 2018). Government data on cloud must stay in India, with providers empanelled by MeitY, the IT ministry. Under India's privacy law, the DPDP Act, the government can require some large data handlers to keep specified data in India; the main duties apply from 13 May 2027. For a bank, insurer or government supplier, an open model on a server in India that only you use is the easiest setup to explain to an auditor (see bare metal vs cloud GPUs). General information, not legal advice: check with counsel, and see hosting your GPUs in India.

Distance matters for voice: the big Indian cities are 13 to 27 ms from Mumbai on the public internet.

Running Sarvam models on GPUs in India

Sarvam and other Indian-language models whose data has to stay in the country need servers in India, one of our six regions; FlexiCloud itself is based in Kochi. We source single-tenant 8-GPU H100, H200, B200 and B300 servers there from verified operators, on terms of a year or more paid upfront, not hourly, sized to your model, context and traffic. Your team runs the serving software. If anyone we recommend pays us, we tell you in writing before you sign. See B300 servers in India and our India data centre guide.

For a quote in India, send us your requirements or book a call.

Where these figures come from

Checked on 19 November 2026 unless a date is given. US dollars at ₹95.25 per US$, as on our other India pages.

Frequently asked questions

What is the best Indian AI model in 2026?
As of November 2026, Sarvam 105B is the strongest Indian open model on independent tests: 18 on Artificial Analysis’s Intelligence Index in April 2026, against 33 for OpenAI’s gpt-oss-120B. Those scores are on the index version used then and cannot be compared with its current v5 scores. Sarvam 105B is free for commercial use under Apache 2.0.
What GPU do I need to run Sarvam 105B?
Sarvam 105B’s full-precision (BF16) weights take about 212 GB, so it needs at least four 80 GB H100s, and one 8-GPU H100, H200 or B200 server for production. Its FP8 build, about 106 GB, fits on one H200 or B200 for light use. These are our estimates.
Can I use Sarvam’s models commercially?
Yes. Sarvam 30B, Sarvam 105B, the November 2026 Sarvam-105B-1711 update and Prism are released under Apache 2.0, which allows commercial use and changes. The older Sarvam-1 has a non-commercial licence.
Is BharatGen’s Param2 open source?
No. Param2 is open-weight: its weights are public, but under a BharatGen non-commercial licence, so it is not open source. Ask BharatGen before using it in a paid product.
Why do Indian languages cost more on AI APIs?
APIs charge per token, and many tokenizers cut Indian scripts into far more pieces than English. On the same FLORES-200 sentences, GPT-4’s tokenizer needed about 4.8 times as many tokens as English for Hindi and 9 times for Malayalam (Petrov et al., 2023). Newer tokenizers narrow the gap: GPT-4o’s cut token counts by about 64% for Hindi and 79% for Malayalam in a Microsoft test.
How much does IndiaAI GPU compute cost, and who can use it?
IndiaAI’s reference on-demand rates (13 March 2026) work out to ₹153 per GPU-hour for an H100, ₹140.63 for an H200 and ₹323 for a B200. IndiaAI calls them indicative and does not say whether they include the subsidy of up to 40% that eligible users can get. Only eligible users can apply, such as startups and MSMEs (with DPIIT recognition, ₹50 lakh of revenue or ₹1 crore of funding), researchers, students and government bodies.
Do I have to run AI models on GPUs in India?
Not by a general law. But payment data (under RBI rules) and government data on cloud must stay in India, so if your prompts or outputs include them, a simple setup is an open model on GPUs in India. Check your own case with counsel.
Can FlexiCloud help me run Indian AI models on GPUs in India?
Yes, by sourcing and sizing the hardware. FlexiCloud is based in India and sources dedicated 8-GPU H100, H200, B200 and B300 servers from verified operators in India and five other regions, on terms of at least one year, billed upfront. Tell us the model, context length and traffic, and we will size the server and come back with options; you run the model software.

Need GPU capacity?

Tell us your GPU count, term and region. We source the best-fit nodes across our provider network in North America, the UK, Europe, India, Asia Pacific and the Gulf, and confirm availability and lead time for your region before you order.