sarvam-105b
Sarvam-105B is an advanced Mixture-of-Experts (MoE) model with 10.3B active parameters, designed for superior performance across a wide range of complex tasks.
text → text · made by Sarvam AI
Sold by
Nobody in the catalogue publishes a price for this yet.
About
sarvam-105b — a text model from Sarvam AI.
It takes text and returns text, with a context window of 131,072 tokens. It was published in March 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- Sarvam AI
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 131,072 tokens
- Published
- March 2026
- Parameters
- 105 billion · read from its own name
- Licence
- apache-2.0
Known as 1 name
sarvamai/sarvam-105b