Deploying DiffusionGemma-Jev (djev) just got a lot easier.
@googlegemma111K followers
647,721 views
31 Comments
Comments from the original post on X (Twitter)

@googlegemma
Credits to @mmastrac and @dylayed. Original post:
22 likes

@jonsouyang
@bodonoghue85 Fastest bookmark of my life
10 likes

@_VirenKhandal
jev on blackwell in the big 2026 🥀 what are we doing
9 likes

@ORC_Killer
but why ? jev is cheaper than $3/h and way better at it
5 likes

@Everlier
Infinite Jev unlocked
4 likes

@duummbass
Put some pressure on Gemini team so you guys can distill for Gemma 5 soon 😌
3 likes

@iMuffined
this is exactly, what i asked for. thanks!
1 like

@MyshinskyYA
This is the kind of deployment UX that makes experimentation actually accessible. Spin it up when you need it, pay while it runs, and let it disappear when you’re done. 🔥
1 like

@ibs4lif
When I was seeing Jev explanation I was asking myself, isn't what DiffusionGemma already doing. Is it the similar, is it that Jev just has more hype?
1 like

@RightHonorableB
Coming to the Gemini API/AI Studio?
1 like

@ntf__sadnan
lmao, didnt see this coming
1 like

@TheAIShrink
Single-ste latency is the real flex. 35ms means you can feel the stream before your coffee cools, smooth workflow vibes that actually respect a mom’s attention span. Efficient code looks good on everyone. 😊
1 like

@tensorquay
One practical limit in the repo: the Cloud Run recipe is set to one GPU instance and 32 concurrent requests. The 100–123 req/s figure is a warm batch result; it says little about the wait a new caller sees when that GPU is busy.
1 like

@pysolin
google's like you want ML, we got ML

@formlesstrades
Oh ok Google.

@brunob_santanna
Interesting! How does this compare to running similar models on other serverless platforms like AWS Lambda or Azure Functions in terms of cost and cold start times?

@KyleRayKelley
@mmastrac you mad lad

@johnroodepic
Don't add --cpu-boost by reflex here. The repo reports 73-75s cold starts with it versus 47.5s without it on the 20-vCPU GPU setup.

@JhonDennisxiud
一条命令就能把实验跑起来 这种少折腾的升级最有用 普通人不用先学一堆黑话

@liuzhao_666
The interesting part is the deployment contract: Jev-compatible API, scale-to-zero, and a single Cloud Run command. The next useful artifact is a cold-start and tail-latency trace under real bursty traffic, because “$0 when idle” matters only when wake-up cost stays predictable.










