Qwen3.8-27B: slower tokens, faster and better results
Qwen3.8-27B, released Friday, delivers better wall-clock results despite slower tokens per second, making 32 GB VRAM useful. The author tested it on real codebases over three days, arguing that xhigh reasoning effort is not wasteful and that 8-bit quants beat 4-bit.
1 source
AI Models by email
Get an email when there's news on AI Models
No news that day, no email.
More stories today
- Lyte closes $165M round at $1.6B valuation
- Meta settlement could clear way for new AI product launches
- Z.ai opens first Tmall store for AI subscriptions
- Fable 5.1 Max users share setup tips and warnings
- Opinion: Next DSM should assess algorithms' role in eating disorders