Inworld Inference launches Gemma 4 31B Fast
What happened
Inworld AI says its Inference service now hosts Google's Gemma 4 31B Fast open-weight model Inworld says the model runs faster on its GPUs with optimized serving. It supports a 256K-token context window, can understand both text and images, and includes a built-in reasoning mode. The news comes from an Inworld AI post on X. So far it is only the company's own announcement. No independent coverage or third-party testing has yet confirmed the claims about speed or performance.
AI-written from the coverage · updated 26 d ago
Coverage timeline
Follow the coverage to see the story from different sides.
- Inworld AIInworld Inference launches Gemma 4 31B Fast
Gemma 4 31B Fast is now live on Inworld Inference. - Google's 31B open-weight model, served faster and optimized on Inworld's GPUs - 256K-token context - Supports text and image understanding - Built-in reasoning mode Try it with your own prompts: https://inworld.ai/model