@LinusEkenstam: I love seeing how fast the frontier labs are jumping in on creating forks. Just today we’ve seen omni-jev and now djev …
Summary
Google Gemma team has released DiffusionGemma-Jev (djev), a fork of JEV, simplifying deployment on Google Cloud Run with performance metrics of ~35-60 ms latency and batch processing at 100-123 requests per second.
View Cached Full Text
Cached at: 09/24/26, 02:18 AM
I love seeing how fast the frontier labs are jumping in on creating forks.
Just today we’ve seen omni-jev and now djev from Google Gemma team.
It will be clear in a few weeks, just how powerful JEV is going to be inside harnesses and applications.
Google Gemma (@googlegemma): Deploying DiffusionGemma-Jev (djev) just got a lot easier. You can now spin up a Jev API-compatible endpoint on Google Cloud Run using a single command.
Performance is solid: ~35-60 ms for single step latency and batch@32 is ~100-123 requests/sec.
It’s a straightforward way to
Similar Articles
DiffusionGemma
Google released DiffusionGemma, an open-weight text generation model (26B parameters, 4B active) under Apache 2 license, demonstrating high inference speeds via NVIDIA's NIM cloud API.
@mervenoyann: DiffusionGemma is out it's compute-bound so 4x faster compared to other Gemma-4 models (1k tok/s on H100) also great on…
DiffusionGemma is out; it's compute-bound and 4x faster than other Gemma-4 models with 1k tok/s on H100, and excels at coding tasks including 3D generation and front-end.
@volokuleshov: Congratulations to Google on open-sourcing Gemma Diffusion! I want to give a shout-out to a group of really talented Co…
Google has open-sourced DiffusionGemma, a novel diffusion-based text generation model that uses block diffusion and efficient encoder-decoder techniques, with contributions from Cornell University researchers.
DiffusionGemma: 4x Faster Text Generation
Google introduces DiffusionGemma, an experimental 26B MoE open model that achieves up to 4x faster text generation on GPUs using text diffusion, targeting speed-critical interactive local workflows.
@DataChaz: One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The @googlegemma team just dropped a MASSIVE dem…
Google's Gemma team released a demo for Gemma 4 26B that runs 10 parallel agents locally at 100+ tokens/second, enabling tasks like coding SVG galleries and parallel translation, all free and open-source.