ainewsblitz.com

Breaking

Qwen3.8-27B Hits 240K Multimodal Context on a Single 24GB RTX 4090

  • Foundation Models
  • Open Source

Local testers have run Qwen3.8-27B, Qwen's new 27-billion-parameter open-weight vision-language model, at up to 240,000 tokens of multimodal context on a single NVIDIA RTX 4090 with 24GB of VRAM by quantizing the key-value cache. The official model card lists a native window of 262,144 tokens, Apache 2.0 weights, and optional extension to one million tokens with YaRN.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,588 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year