BLAST RADIUS

Open-weight & owned stack · Training tuning

MindStudio Evaluates Qwen3.8 Swift Fine-Tune

Sep 19, 2026

MindStudio reported that the Qwen3.8 27B Swift fine-tune used more tokens and tool calls but completed a coding benchmark faster.

Read the original at mindstudio.aiOpens the publisher's site in a new tab

More in Open-weight & owned stack