India's Sarvam launches Token Factory: 8 open models, 0.2s TTFT on a B200 cluster
itsOmSarraf_ · x · 2026-11-16
Indian AI firm Sarvam announced Token Factory, an inference platform exposing 8 open models through one OpenAI-compatible API. Claimed numbers: 0.2s time-to-first-token at 330 tokens/s for Sarvam 105B, 5x faster TTFT for Gemma 4 31B versus other providers, 450B+ tokens served daily including DeepSeek V4.1 Flash, and 95.7% of prompt tokens served from cache. It runs on India's largest B200 cluster, aiming to make top open models accessible at scale.
More from Infra
- A 10-item beginner reading list for LLM distributed training, from Horovod to FSDP — East-Muffin-6472 · 2026-11-17
- 18MB browser-run TTS model tiny-voca makes paid English TTS look silly — thisdudelikesAI · 2026-11-17
- Replicate quietly switches nano banana outputs from JPG downloads to presigned URLs — Kyrannio · 2026-11-17
- Fireworks AI tells investors chips are a commodity, its moat is software that runs models fast — hargup13 · 2026-11-17
- Claude-written CUDA C++ port runs TRELLIS.2 5.3x faster on H200, bit-identical — huggingface · 2026-11-17
- China to make 3M AI ASICs in 2027 vs West's 20M, each ~4x faster per chip — teortaxesTex · 2026-11-17