Today for AI
HOT RADAR
llmHEAT 11.5°

AI CLUSTERED EVENT · 10/9/2026

JetBrains Releases Mellum2.1: RL Enhances Agentic Coding with Throughput Nearly Double Qwen3.5-9B

1 reports archived1 independent sourcesupdated 10/9/2026, 12:59:08
Synthesis & Latest Updates
1 Sources Cross-Validated

JetBrains released the open-source Mellum2.1 model, significantly enhancing agentic coding capabilities by expanding reinforcement learning as a core training phase. The model achieves nearly double the high-load inference throughput of Qwen3.5-9B on H200 GPUs and supports local deployment for code privacy.

LATEST/JetBrains released the open-source Mellum2.1 model, significantly enhancing agentic coding capabilities by expanding reinforcement learning as a core training phase. The model achieves nearly double the high-load inference throughput of Qwen3.5-9B on H200 GPUs and supports local deployment for code privacy.

HEAT TRENDHourly heat curve

3 fully observed hours
Now
11.7
Peak
12.013:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. IT之家 · 智能时代T2·78 pts

    JetBrains Releases Mellum2.1: RL Enhances Agentic Coding with Throughput Nearly Double Qwen3.5-9B

    Original: JetBrains 编程 AI 模型 Mellum2.1 发布：高负载推理吞吐量近 Qwen3.5-9B 两倍

    • Mellum2.1 retains the 12B MoE architecture (2.5B active parameters) under Apache 2.0 license.
    • Key upgrade involves expanding RL from a final stage to a main training phase, improving root cause analysis and fix verification.
    • High-load inference throughput is nearly double that of Qwen3.5-9B, with single-request speed up by ~1.6x.