Sarvam 105B 1711

Released
2026-11-17
Last refreshed
2026-11-18
Status
Researched today
Open sourceCommercial use: permittedRAGAgentsLong contextJSON / Tool use

Sarvam 105B 1711 is a released rag, agents, and long context model with open-source and 160K context; evaluate it while provider pricing coverage matures.

Sarvam.ai releases · 3 in the last 12 monthsChangelog →
Specifications
Family
Sarvam
Released
2026-11-17
Context
160K
Parameters
105B (10.3B active)
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by

Multilingual Voice AI for India

Bengaluru, India
Founded 2023
Website
Pricing

No tracked provider pricing is available yet.

About

Sarvam 105B 1711 is Sarvam AI’s post-trained update to its 105B mixture-of-experts model. It targets tool calling, instruction following, agentic tasks and Indian languages. The maker publishes BF16 and NVFP4 builds of the same checkpoint, with self-hosted vLLM instructions.

Providers

No active provider routes are tracked for this model yet.

Capabilities

JSON / Tool use

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.