Sarvam LLM
Shares rank 33 of 39 open-weight language models by recommenders
Indian open-weight language model praised for being trained from scratch, cheap, and strong on local languages. Critics say it hallucinates and lacks transparency about its claims.
Indian open-weight language model praised for being trained from scratch, cheap, and strong on local languages. Critics say it hallucinates and lacks transparency about its claims.
16 people gave an opinion
- recommend it
- 8
- criticize it
- 8
- approval share
- 50%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 8 people recommend itNeeds 10 or more, not met.
- 1 recommender for every criticNeeds 2 to 1 or better, not met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Solid results for a first release
“I’ve played around with the 26b parameter model and it’s pretty solid.”
Comment from 15 Jun 2026 in “India, UAE partner on AI sovereignty to bypass Google, Microsoft” “These look like good results for a first model release.”
Comment from 7 Mar 2026 in “Sarvam 105B, the first competitive Indian open source LLM” Accurate answers with few errors
“which sarvam got done with 99% accuracy leaving one text error”
Comment from 23 Jun 2026 in “Mistral OCR 4” “it gave good, unbiased answers, giving a good holistic picture”
Comment from 7 Mar 2026 in “Sarvam 105B, the first competitive Indian open source LLM”
What people warn about
Each mark is one comment
Hallucinates confidently, lies
“it confidently lies / hallucinates without a hint of remorse”
Comment from 7 Mar 2026 in “Sarvam 105B, the first competitive Indian open source LLM” “the hallucinations produced by the model when I poked at it reminded me of model responses before the last couple of years of work”
Comment from 7 Mar 2026 in “Sarvam 105B, the first competitive Indian open source LLM” Lacks transparency about its claims
“It's "open weights" not "open source" and many other (problematic) things”
Comment from 7 Mar 2026 in “Sarvam 105B, the first competitive Indian open source LLM” “The claims are bold. The receipts are missing.”
Comment from 19 Feb 2026 in “Could Sarvam 30B/105B Models Be India's Answer to DeepSeek and Mistral?” Weak on domain-specific tasks
“Does not handle critical inputs even for moderation tasks”
Comment from 7 Mar 2026 in “Sarvam 105B, the first competitive Indian open source LLM” “Domain specific models simply don’t work. Ever.”
Comment from 13 Apr 2026 in “India's frugal AI models are a blueprint for resource-strapped nations”
Other open-weight language models people recommend
The four most recommended other open-weight language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Qwen 3.8 27B | 1,173 | 426 | 73% | 13 | 2 mo32 owners | Approved |
| Z.ai GLM | 1,043 | 384 | 73% | 13 | 2 mo52 owners | Approved |
| Kimi | 931 | 359 | 72% | 13 | 1 mo26 owners | Approved |
| Gemma 4 | 713 | 249 | 74% | 13 | 1 mo14 owners | Approved |
| Sarvam LLMThis page | 8 | 8 | 50% | 4 | — | — |
What people said
17 of the 20 comments that mention it, newest first. Each links to the original comment.
“seems like a model from a year ago”
“which sarvam got done with 99% accuracy leaving one text error”
“I’ve played around with the 26b parameter model and it’s pretty solid.”
“For its use cases I feel like India’s Sarvam is doing better.”
“see sarvam.ai and their tokenisation improvements on local languages”
“India is going the better route with Sarvam which is trained from scratch and still relatively cheap”
“Domain specific models simply don’t work. Ever.”
“the hallucinations produced by the model when I poked at it reminded me of model responses before the last couple of years of work”
“it gave good, unbiased answers, giving a good holistic picture”
“They've also not bothered with upstreaming the model arch to transformers and require remote code for their modeling code to run”
“it confidently lies / hallucinates without a hint of remorse”
“I don't know what that means without some code and proper context.”
“It's "open weights" not "open source" and many other (problematic) things”
“These look like good results for a first model release.”
“Does not handle critical inputs even for moderation tasks”
“I have great respect for Sarvam and the team behind it.”
“The claims are bold. The receipts are missing.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.