4 min read
Qwen3.8-27B on 17GB: what Unsloth's day-zero release…
Alibaba's Qwen3.8-27B fits on a single RTX 4090 with Unsloth's Dynamic GGUF quants. Day-zero fine-tuning support makes local agent stacks practical.
5 min read
Tinker lets you fine-tune big models without…
Thinking Machines Lab's Tinker API runs distributed LoRA training while you write a normal Python loop on your laptop. Here's how it fits the Cursor playbook for teams that are not Cursor.