Sarvam releases Sarvam-105B-1711 open-weight model
Understand this story
Sarvam AI has released Sarvam-105B-1711, a new open-weight checkpoint of Sarvam 105B, and it is now live on Sarvam Token Factory. Sarvam AI says the checkpoint's average score across eight conversational agent benchmarks rose from 42.6 in the February version to 74.5, and the blended price dropped from $0.44 per million tokens to $0.15. The weights are published on Hugging Face, including a BF16 version and a 65 GB NVFP4 version that can run on a single workstation GPU.
AI overview based on source reports · Updated 19 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Sarvam AI BlogFeaturedIntroducing Sarvam-105B-1711
Sarvam released Sarvam-105B-1711, an open-weight Flash-Lite checkpoint of Sarvam 105B trained on upgraded B200 infrastructure, with weights on Hugging Face in BF16 and a 65 GB NVFP4 version that runs on a single workstation GPU. Its average across eight conversational agent benchmarks rose from 42.6 to 74.5 versus the February release, and inference optimisations cut its blended price from $0.44 to $0.15 per million tokens. The company reports it matches Gemini 3.5 Flash-Lite and Gemma 4 31B at a fraction of their price, with large gains on IFBench (32.5 to 82.5), Tau2 (46.2 to 85.5) and its Indic suite (30.1 to 79.1).
Activity for this story
Not enough continuous observations to show a trend yet.