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.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.