Qwen3 8B
on M2 Max 96GB · Ollama
Use cases
visioncoding
Summary
User reports a VLM is best overall for OCR and detail extraction, correctly reading mixed-script text (Chinese + Latin) and catching fine details other models missed.
Output is verbose at 1.4-2.2k tokens.
The user recommends it as the default for a coding-assistant MCP.