Levelmodel
ClassLLM
Parameters105B
Context128,000
ReleasedMar 2026
Opennessopen weights permissive
Runs onsingle datacentre GPU
Statusactive
Benchmark Results
vendor-reportedindependent
Artificial Analysis Intelligence Index v4.3.2composite index
high; asterisk on pageindependent
9
03060
Score in index. Higher is better.
AA leaderboard, 205 current models
GPQA Diamondknowledge and reasoning
vendor-reported
78.7
050100
Score in %. Higher is better.
MMLU-Proknowledge and reasoning
vendor-reported
81.7
050100
Score in %. Higher is better.
SWE-bench Verifiedcoding
vendor-reported
45
050100
Score in %. Higher is better.
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- MoE MoE with MLA-style attention (128 experts, top-8 + 1 shared)
- Total parameters
- 105B sources
- Active parameters
- 10.3B
- Checkpoint parameters
- –
- Note
- Context 128K via YaRN
- Context length
- 128,000 tokens
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- single datacentre GPU
- Footprint
- Single GPU at FP8; GGUF variant
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- Indic focus
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperSarvam AIstartup, India
Sarvam AIstartup, IndiaModelSarvam 105BSarvam AI, LLM
Sarvam 105BSarvam AI, LLMR&D TopicsOpen-Weight Frontier Releases as Research SubstrateRegional or National Foundation Model Training (Continued Pretraining at 7B to 70B)
Use CasesIndonesian and Regional-Language LLMsPublic SectorBanking Customer Service AssistantsFinanceCitizen Service AssistantsPublic SectorClinical LLM (Open Weights)Healthcare+3 moreUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026
PT PegadaianIn production, 5 Jun 2026
Bank Central Asia (BCA)In production, 16 Mar 2026Bank Central Asia (BCA)In production, 16 Mar 2026+14 moreDeployments of these use cases; none names this model.
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026PT PegadaianIn production, 5 Jun 2026Bank Central Asia (BCA)In production, 16 Mar 2026Bank Central Asia (BCA)In production, 16 Mar 2026+14 moreDeployments of these use cases; none names this model.Organisations 1
R&D topics 2
Open-Weight Frontier Releases as Research SubstrateUsing released weights as the base for downstream research.used byRegional or National Foundation Model Training (Continued Pretraining at 7B to 70B)Pretraining or continued pretraining a mid-size model to serve a national or regional lan…produced by
Sources
- Blog - Sarvam AI sarvam.ai https://www.sarvam.ai/blogs
- LLM Leaderboard - Comparison of AI models from OpenAI, Anthropic, Google, SpaceXAI & others | Artificial Analysis artificialanalysis.ai https://artificialanalysis.ai/leaderboards/models
- huggingface.co/sarvamai https://huggingface.co/sarvamai
- huggingface.co/sarvamai/sarvam-105b https://huggingface.co/sarvamai/sarvam-105b
- huggingface.co/sarvamai/sarvam-105b/raw/main/README.md https://huggingface.co/sarvamai/sarvam-105b/raw/main/README.md
- huggingface.co/api/models/sarvamai/sarvam-105b https://huggingface.co/api/models/sarvamai/sarvam-105b
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Sarvam 105B", https://aurion.semai.id/models/sarvam-ai-sarvam-105b/, records of October 2026.