{"schema_version":"onlylabs.public_signal.v1","title":"Sarvam AI Model: sarvamai/sarvam-m","description":"Sarvam AI model signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/c42fdf60-e06d-473c-86cf-eb7ffd0a3b04","json_url":"https://onlylabs.fyi/signals/c42fdf60-e06d-473c-86cf-eb7ffd0a3b04/signal.json","generated_at":"2026-06-11T02:50:42.753335+00:00","org":{"slug":"sarvam","name":"Sarvam AI","category":"neolab","category_label":"Neolab","dossier_url":"https://onlylabs.fyi/labs/sarvam","dossier_json_url":"https://onlylabs.fyi/labs/sarvam/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/c42fdf60-e06d-473c-86cf-eb7ffd0a3b04","signal_json":"https://onlylabs.fyi/signals/c42fdf60-e06d-473c-86cf-eb7ffd0a3b04/signal.json","source":"https://huggingface.co/sarvamai/sarvam-m","lab_dossier":"https://onlylabs.fyi/labs/sarvam","lab_dossier_json":"https://onlylabs.fyi/labs/sarvam/dossier.json","analysis":"https://onlylabs.fyi/analysis/sarvam","analysis_json":"https://onlylabs.fyi/analysis/sarvam/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/sarvam/evidence.json","category":"https://onlylabs.fyi/neolabs","category_json":"https://onlylabs.fyi/neolabs.json","category_feed":"https://onlylabs.fyi/neolabs/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neolab","topic":"https://onlylabs.fyi/topics/releases","topic_signals_json":"https://onlylabs.fyi/topics/releases/signals.json?category=neolab","topic_feed":"https://onlylabs.fyi/topics/releases/feed.xml?category=neolab","data_business":null},"answer_pack":{"answer":"Sarvam AI published sarvamai/sarvam-m. This model signal is evidence of what shipped on model infrastructure and how the release is positioned. High-signal details: license apache-2.0 · 4.6K HF downloads · Notable model release with moderate traction.. onlylabs links this event to 1 captured evidence page and 6 related model signals.","signal_desk":"releases","source_context":{"source_url":"https://huggingface.co/sarvamai/sarvam-m","source_host":"huggingface.co","occurred_at":"2025-05-20T06:39:05+00:00","first_seen_at":"2026-06-06T01:49:35.761387+00:00","date_source":"source","context":null},"context_markers":[{"label":"Lab","value":"Sarvam AI","source":"signal"},{"label":"Signal desk","value":"releases","source":"signal"},{"label":"Source host","value":"huggingface.co","source":"source"},{"label":"Task","value":"text-generation","source":"model"},{"label":"License","value":"apache-2.0","source":"model"},{"label":"Library","value":"transformers","source":"model"},{"label":"Params","value":"23.6B","source":"model"},{"label":"Downloads","value":"4.6K","source":"traction"},{"label":"Likes","value":"344","source":"traction"},{"label":"Notability","value":"Notable model release with moderate traction.","source":"signal"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Model card","source":"model"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://huggingface.co/sarvamai/sarvam-m/raw/main/README.md"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T02:50:42.753335+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/c42fdf60-e06d-473c-86cf-eb7ffd0a3b04/signal.json","dossier_json":"https://onlylabs.fyi/labs/sarvam/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/sarvam/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/sarvam/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/releases/signals.json?category=neolab","topic_feed":"https://onlylabs.fyi/topics/releases/feed.xml?category=neolab","category_signals_json":"https://onlylabs.fyi/signals.json?category=neolab","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn model cards, repository releases, and launch artifacts into a current view of what shipped and what changed.","evidence_focus":["model card","release note","version or tag","pipeline tag","license","downloads, likes, stars, and linked papers"],"extraction_questions":["What actually shipped, and through which public artifact?","Which releases include inspectable model, repo, paper, or package evidence?","Which launches create new eval, data, infra, or deployment needs?","Which shipped signals are missing captured page context?"],"signal_questions":["What shipped in this model artifact, and what evidence describes its capability, license, or traction?","What actually shipped, and through which public artifact?","Which releases include inspectable model, repo, paper, or package evidence?","Do the 6 related model signals show a repeated pattern?"],"output_fields":["org","release_type","artifact","traction","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, keep conclusions tied to category-specific strategy, source evidence, and follow-up questions.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/c42fdf60-e06d-473c-86cf-eb7ffd0a3b04/signal.json","required":true},{"label":"source","url":"https://huggingface.co/sarvamai/sarvam-m","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/sarvam/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/sarvam/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/releases/signals.json?category=neolab","required":false},{"label":"data_radar_json","url":null,"required":false}],"expected_output":["one-paragraph source-grounded interpretation","category-specific implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze Sarvam AI's model signal \"sarvamai/sarvam-m\" for neolab strategy."},"semantic_triples":[{"subject":"Sarvam AI","predicate":"published model","object":"sarvamai/sarvam-m","text":"Sarvam AI published model sarvamai/sarvam-m."},{"subject":"sarvamai/sarvam-m","predicate":"is classified as","object":"model signal","text":"sarvamai/sarvam-m is classified as model signal."},{"subject":"sarvamai/sarvam-m","predicate":"belongs to","object":"releases desk","text":"sarvamai/sarvam-m belongs to releases desk."},{"subject":"sarvamai/sarvam-m","predicate":"has evidence coverage","object":"1 captured evidence page","text":"sarvamai/sarvam-m has evidence coverage 1 captured evidence page."},{"subject":"sarvamai/sarvam-m","predicate":"has captured page count","object":"1","text":"sarvamai/sarvam-m has captured page count 1."},{"subject":"sarvamai/sarvam-m","predicate":"has readable page count","object":"1","text":"sarvamai/sarvam-m has readable page count 1."},{"subject":"sarvamai/sarvam-m","predicate":"has related signal count","object":"6","text":"sarvamai/sarvam-m has related signal count 6."},{"subject":"sarvamai/sarvam-m","predicate":"has analysis playbook objective","object":"Turn model cards, repository releases, and launch artifacts into a current view of what shipped and what changed.","text":"sarvamai/sarvam-m has analysis playbook objective Turn model cards, repository releases, and launch artifacts into a current view of what shipped and what changed.."},{"subject":"sarvamai/sarvam-m","predicate":"has source host","object":"huggingface.co","text":"sarvamai/sarvam-m has source host huggingface.co."},{"subject":"sarvamai/sarvam-m","predicate":"has lab","object":"Sarvam AI","text":"sarvamai/sarvam-m has lab Sarvam AI."},{"subject":"sarvamai/sarvam-m","predicate":"has signal desk","object":"releases","text":"sarvamai/sarvam-m has signal desk releases."},{"subject":"sarvamai/sarvam-m","predicate":"has source host","object":"huggingface.co","text":"sarvamai/sarvam-m has source host huggingface.co."},{"subject":"sarvamai/sarvam-m","predicate":"has task","object":"text-generation","text":"sarvamai/sarvam-m has task text-generation."},{"subject":"sarvamai/sarvam-m","predicate":"has license","object":"apache-2.0","text":"sarvamai/sarvam-m has license apache-2.0."},{"subject":"sarvamai/sarvam-m","predicate":"has library","object":"transformers","text":"sarvamai/sarvam-m has library transformers."},{"subject":"sarvamai/sarvam-m","predicate":"has params","object":"23.6B","text":"sarvamai/sarvam-m has params 23.6B."},{"subject":"sarvamai/sarvam-m","predicate":"has downloads","object":"4.6K","text":"sarvamai/sarvam-m has downloads 4.6K."}]},"intelligence":{"signal_desk":"releases","answer":"Sarvam AI published sarvamai/sarvam-m. This model signal is evidence of what shipped on model infrastructure and how the release is positioned. High-signal details: license apache-2.0 · 4.6K HF downloads · Notable model release with moderate traction.. onlylabs links this event to 1 captured evidence page and 6 related model signals.","semantic_triples":[{"subject":"Sarvam AI","predicate":"published model","object":"sarvamai/sarvam-m","text":"Sarvam AI published model sarvamai/sarvam-m."},{"subject":"sarvamai/sarvam-m","predicate":"is classified as","object":"model signal","text":"sarvamai/sarvam-m is classified as model signal."},{"subject":"sarvamai/sarvam-m","predicate":"belongs to","object":"releases desk","text":"sarvamai/sarvam-m belongs to releases desk."},{"subject":"sarvamai/sarvam-m","predicate":"has evidence coverage","object":"1 captured evidence page","text":"sarvamai/sarvam-m has evidence coverage 1 captured evidence page."}]},"signal":{"id":"c42fdf60-e06d-473c-86cf-eb7ffd0a3b04","url":"https://onlylabs.fyi/signals/c42fdf60-e06d-473c-86cf-eb7ffd0a3b04","json_url":"https://onlylabs.fyi/signals/c42fdf60-e06d-473c-86cf-eb7ffd0a3b04/signal.json","source_url":"https://huggingface.co/sarvamai/sarvam-m","title":"sarvamai/sarvam-m","summary":"Sarvam AI published a model signal. onlylabs watches model cards, launch context, and traction.","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"sarvam","name":"Sarvam AI","category":"neolab"},"occurred_at":"2025-05-20T06:39:05+00:00","first_seen_at":"2026-06-06T01:49:35.761387+00:00","date_source":"source","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://huggingface.co/sarvamai/sarvam-m/raw/main/README.md"]},"facets":{"pipeline_tag":"text-generation","license":"apache-2.0"},"traction":{"github_stars":null,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":4612,"hf_likes":344},"data_radar":null},"primary_evidence_page":{"url":"https://huggingface.co/sarvamai/sarvam-m/raw/main/README.md","final_url":"https://huggingface.co/sarvamai/sarvam-m/raw/main/README.md","title":"sarvamai/sarvam-m model card","http_status":200,"content_type":"text/plain; charset=utf-8","capture_method":"plain","fetched_at":"2026-06-11T02:50:42.753335+00:00","bytes":6239,"raw_path":"0eeed0c4ba82dd0c0418a3bce736b42fe8905e56bc6c97c00640d11b246720d4.md","content_hash":"b05f985c708c4ef07dccfd0faf600232f8579c092e78076dae0c185de2daca6c","excerpt_chars":1200,"truncated":true,"excerpt":"--- library_name: transformers license: apache-2.0 language: - en - bn - hi - kn - gu - mr - ml - or - pa - ta - te base_model: - mistralai/Mistral-Small-3.1-24B-Base-2503 base_model_relation: finetune --- Sarvam-M

\"Chat

Model Information `sarvam-m` is a multilingual, hybrid-reasoning, text-only language model built on Mistral-Small. This post-trained version delivers exceptional improvements over the base model: - +20% average improvement on Indian language benchmarks - +21.6% enhancement on math benchmarks - +17.6% boost on programming benchmarks Performance gains are even more impressive at the intersection of Indian languages and mathematics, with an outstanding +86% improvement in romanized Indian language GSM-8K benchmarks. Learn more about sarvam-m in our detailed [blog post](https://www.sarvam.ai/blogs/sarvam-m). Key Features - **Hybrid Thinking Mode**: A single versatile model supporting both \"think\" and..."},"evidence_pages":[{"url":"https://huggingface.co/sarvamai/sarvam-m/raw/main/README.md","final_url":"https://huggingface.co/sarvamai/sarvam-m/raw/main/README.md","title":"sarvamai/sarvam-m model card","http_status":200,"content_type":"text/plain; charset=utf-8","capture_method":"plain","fetched_at":"2026-06-11T02:50:42.753335+00:00","bytes":6239,"raw_path":"0eeed0c4ba82dd0c0418a3bce736b42fe8905e56bc6c97c00640d11b246720d4.md","content_hash":"b05f985c708c4ef07dccfd0faf600232f8579c092e78076dae0c185de2daca6c","excerpt_chars":1200,"truncated":true,"excerpt":"--- library_name: transformers license: apache-2.0 language: - en - bn - hi - kn - gu - mr - ml - or - pa - ta - te base_model: - mistralai/Mistral-Small-3.1-24B-Base-2503 base_model_relation: finetune --- Sarvam-M

\"Chat

Model Information `sarvam-m` is a multilingual, hybrid-reasoning, text-only language model built on Mistral-Small. This post-trained version delivers exceptional improvements over the base model: - +20% average improvement on Indian language benchmarks - +21.6% enhancement on math benchmarks - +17.6% boost on programming benchmarks Performance gains are even more impressive at the intersection of Indian languages and mathematics, with an outstanding +86% improvement in romanized Indian language GSM-8K benchmarks. Learn more about sarvam-m in our detailed [blog post](https://www.sarvam.ai/blogs/sarvam-m). Key Features - **Hybrid Thinking Mode**: A single versatile model supporting both \"think\" and..."}],"related_signals":[{"id":"7dc590e1-15e2-465e-80c4-d7679d3b0d68","url":"https://onlylabs.fyi/signals/7dc590e1-15e2-465e-80c4-d7679d3b0d68","source_url":"https://huggingface.co/sarvamai/sarvam-105b","title":"sarvamai/sarvam-105b","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"sarvam","name":"Sarvam AI","category":"neolab"},"occurred_at":"2026-03-03T13:13:55+00:00","first_seen_at":"2026-06-06T01:49:35.761387+00:00","date_source":"source"},{"id":"27a7f90b-8d29-490f-985e-274f4947fcfb","url":"https://onlylabs.fyi/signals/27a7f90b-8d29-490f-985e-274f4947fcfb","source_url":"https://huggingface.co/sarvamai/sarvam-30b","title":"sarvamai/sarvam-30b","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"sarvam","name":"Sarvam AI","category":"neolab"},"occurred_at":"2026-03-03T12:53:32+00:00","first_seen_at":"2026-06-06T01:49:35.761387+00:00","date_source":"source"},{"id":"d133ad2f-299d-4081-8b45-d6abb7259262","url":"https://onlylabs.fyi/signals/d133ad2f-299d-4081-8b45-d6abb7259262","source_url":"https://huggingface.co/sarvamai/sarvam-translate","title":"sarvamai/sarvam-translate","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"sarvam","name":"Sarvam AI","category":"neolab"},"occurred_at":"2025-06-07T10:13:56+00:00","first_seen_at":"2026-06-06T01:49:35.761387+00:00","date_source":"source"},{"id":"2e2d81ce-54d7-4b9a-8d45-97cfb3aed3a4","url":"https://onlylabs.fyi/signals/2e2d81ce-54d7-4b9a-8d45-97cfb3aed3a4","source_url":"https://huggingface.co/sarvamai/sarvam-1","title":"sarvamai/sarvam-1","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"sarvam","name":"Sarvam AI","category":"neolab"},"occurred_at":"2024-10-23T13:18:53+00:00","first_seen_at":"2026-06-06T01:49:35.761387+00:00","date_source":"source"},{"id":"cdeb5674-6ea6-4403-aea5-0db09be329ae","url":"https://onlylabs.fyi/signals/cdeb5674-6ea6-4403-aea5-0db09be329ae","source_url":"https://huggingface.co/sarvamai/sarvam-1-v0.5","title":"sarvamai/sarvam-1-v0.5","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"sarvam","name":"Sarvam AI","category":"neolab"},"occurred_at":"2024-08-13T07:32:37+00:00","first_seen_at":"2026-06-06T01:49:35.761387+00:00","date_source":"source"},{"id":"186da869-f835-4a0d-8310-2015dd4cadc4","url":"https://onlylabs.fyi/signals/186da869-f835-4a0d-8310-2015dd4cadc4","source_url":"https://huggingface.co/sarvamai/shuka-1","title":"sarvamai/shuka-1","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"sarvam","name":"Sarvam AI","category":"neolab"},"occurred_at":"2024-08-08T21:45:22+00:00","first_seen_at":"2026-06-06T01:49:35.761387+00:00","date_source":"source"}]}