Filter
Exclude
Time range
-
Minimum likes
Halloween 🎃
0
0
12
1,188
Junie Cage is on stage
Head of @Alibaba_Qwen showcase @junie_ai Local at Alibaba Conference
0
0
7
982
Ivan Kuleshov retweeted
For this release of Junie Local, we trained DFlash2 speculators for Qwen-blend-27B and Qwen3.6-27B

To train those drafters, we synthesized a diverse set of agentic trajectories solving SWE tasks

We also shipped a new inference engine based on @inco_ai Splash

open weights ↓
~40 → ~70 tokens/s on M5 Max.
Bursts up to 107. All local.
Junie Local now runs on Splash + DFlash2, with lower memory use and support for M4 Macs (64 GB RAM).

blog.jetbrains.com/junie/2026/10/…
1
1
12
716
107 tokens/second with optimized qwen3.8 on MacBook

blog.jetbrains.com/junie/2026/10/…
0
0
6
1,223
🤗
jetbrains has gifted me this delicate piece of flickering agent tracker it'll absolutely cook my work life balance 🌝
1
0
26
3,358
A photographer from Nvidia was following me for a reason
@NVIDIAGTC Spotted @Merocle in the wild 😃
0
0
3
1,738
Ivan Kuleshov retweeted
Today we're releasing Air Governance.

For CTOs and tech leads: track AI usage, manage access, policies and spend org-wide.

Any LLM provider. Any dev tool. Truly vendor-agnostic.

Top-ups, guardrails, AI metrics, sessions.

Battle-tested at JetBrains. Can't imagine going back.
3
20
95
19,581
My GPU was buffed
27
38
3,865
179,569
GTC Berlin
Jensen on stage
1
0
13
1,243
The newest Datacenter to go from Nvidia
0
3
26
2,533
Ivan Kuleshov retweeted
Junie Local now runs on @NVIDIARTXSpark from day one.

Get a full-fledged coding agent on your PC. It reads your code, edits files, and runs tests. There are no tokens or quotas, and no code leaves the machine.

Windows support is stable, too. All you need is a 24 GB Nvidia RTX junie.jetbrains.com/local
6
13
80
8,533
Ivan Kuleshov retweeted
Today we have hit a new milestone for Junie Local.

It can run on your RTX devices and Windows version is stable.
100% local.
Zero costs.

Available both though Air in IDEs / Junie CLI.
More supported hardware and more powerful models coming soon!
2
6
83
4,309
Now, starting at 24 GB of VRAM on Windows
junie.jetbrains.com/local
0
0
4
1,110
They added a banana for scale 🤣
2
1
81
43,234
Replying to @ShakhizatN76916
@ShakhizatN76916 Here deepseek-v4.1-flash
0
0
1
98
You asked about cooling.
It's all serious, with redundancy
Temporary.

1Tb unified memory, 8x DGX Sparks with 200Gbit interconnection
2
0
43
3,106
Replying to @senadaruc
@senadaruc Two deskpi rack mate screwed together
1
0
1
308
Replying to @wei_wang
@wei_wang "temporary"! 🤣
2
0
4
1,610
Replying to @theBuoyantMan
1
0
9
240