Developer Fine-Tunes 4B Model to Top Decision-Making Benchmarks

A business consultant spent 15 days fine-tuning a Qwen3.5-4B model with LoRA and a small decision head to create ImaJev-4B, which handles text and up to two images and returns probabilities per option. It ranked #1 of 91 on JevBench (67.37) and #3 of 56 on DecisionBench, ahead of GPT-5.6 Luna and DeepSeek V4.1. Total cost about $1,200; weights released under Apache-2.0.

• Open-source Gear framework: a meta-learning tool for RSI2026-11-01
• Developer embeds 32-bit RISC-V CPU inside Qwen model weights2026-10-28
• Open-source Neuron Explorer released for Qwen3.5-4B2026-10-27
• Developer previews 4B coding model that generates 3D scenes2026-10-25
• SWE-Race benchmark tests coding agents on real concurrency bugs2026-10-06