New article out in BMJ Open @bmj.com - making a tool for shared decision making between spine surgeons and patients with XGBoost regression predicting daily function and pain after spine surgery, and a nearest-neighbor lookup to show outcomes from similar cases bmjopen.bmj.com/content/16/5...
bmjopen.bmj.com
![A scatter plot titled “AIME25 — Total Memory vs. Accuracy (Qwen3)” compares model accuracy (%) against total memory usage (weights + KV cache, in GB) for various Qwen3 model sizes and quantization levels.
Axes:
• X-axis: Total Memory (Weight + KV Cache) [GB] (log scale, ranging roughly from 1 to 100)
• Y-axis: Accuracy (%), ranging from 0 to 75
Legend:
• Colors: model sizes —
• 0.6B (yellow)
• 1.7B (orange)
• 4B (salmon)
• 8B (pink)
• 14B (purple)
• 32B (blue)
• Shapes: precision levels —
• Circle: 16-bit
• Triangle: 8-bit
• Square: 4-bit
• Marker size: context length —
• Small: 2k tokens
• Large: 30k tokens
Main trend:
Larger models (rightward and darker colors) achieve higher accuracy but require significantly more memory. Smaller models (left, yellow/orange) stay below 30% accuracy. Compression (8-bit or 4-bit) lowers memory usage but can reduce accuracy slightly.
Inset zoom (upper center):
A close-up box highlights the 8B (8-bit) and 14B (4-bit) models showing their proximity in accuracy despite differing memory footprints.
Overall, the chart demonstrates scaling behavior for Qwen3 models—accuracy grows with total memory and model size, with diminishing returns beyond the 14B range.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:ckaz32jwl6t2cno6fmuw2nhn/bafkreiatqdqcrxckrhsruoka6llaggjdsr3cpgspql5lnn7kttwrx3q7ga)
