JetBrains adds RTX Spark support to Junie Local and makes Windows support stable
Overview
JetBrains announces Day 0 support for Nvidia's RTX Spark platform in Junie Local, its local AI coding tool, and moves Windows support from experimental to stable, according to a JetBrains announcement reported by IThome on October 17.
JetBrains says preliminary tests reach generation speeds of up to 55 tokens per second on RTX Spark.
JetBrains says the tool needs no registration or subscription, charges no token fees, sets no usage quotas, and does not upload code to the cloud. Besides RTX Spark devices, it also runs on RTX GPUs based on Ampere or newer architectures with at least 24GB of VRAM, including the RTX 3090, RTX 4090, and 32GB RTX 5090. Users can choose Qwen3.6-27B or a JetBrains fusion model.
Written by AI from the articles below · updated Oct 17, 7:47 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- IThome · AINewsJetBrains' Junie Local hits 55 tokens per second on Nvidia RTX Spark
AIJetBrains says its local AI coding tool Junie Local is Day 0 compatible with Nvidia's RTX Spark platform, reaching generation speeds of up to 55 tokens per second in preliminary tests. The Windows version has moved from experimental to stable, and the tool needs no registration, subscription, or token fees. It also runs on RTX GPUs with at least 24GB VRAM, such as the RTX 3090, 4090, and 5090 with 32GB, and users can choose Qwen3.6-27B or a JetBrains fusion model.
Heat trend
Not enough continuous observations to show a trend yet.