v4.0.0 v3.3.0
lyogavin/airllmSep 5, 2026 → Aug 28, 20260 days between releases
Generating AI comparison
Analyzing what changed between v4.0.0 and v3.3.0. This page updates automatically — usually within a minute.
The Two Releases
AirLLM v4.0.0 — train Qwen3.8-Flash-Next under 6GB
Sep 5, 2026· 2 months ago
This release introduces a memory-efficient training architecture known as Streamed LoRA, enabling the training of large models like Qwen3.8-Flash-Next on consumer-grade hardware with limited VRAM. It provides updated installation steps and specific usage examples for local dataset training.
Full release notesAirLLM v3.3.0 — Qwen3.8-Flash-Next on 5.95GB
Aug 28, 2026· 2 months ago
This release focuses on optimizing the inference of the Qwen3.8-Flash-Next model, enabling it to run on a single GPU with minimal VRAM usage through advanced streaming techniques.
Full release notes