# Optimisations Wednesday, 25% more throughput than Ollama

> Smarter & deeper MTP, MTPLX, and less CPU/GPU synchronisation on Qwen.

- Author: Luca Lowndes
- Published: 2026-08-26
- Topics: MLX, Qwen, Performance
- Canonical: https://luca.lowndes.net/blog/optimisations-wednesday-25-percent-over-ollama

Hello LinkedIn Fam, welcome to Optimisations Wednesday.

Today's headline is a 25% increase in throughput when compared to Ollama.

How did I do this?

- Smarter & deeper MTP (Qwen's MTP sidecar looks really impressive and I've found acceptance to be quite high)
- Switched to MTPLX (wasn't significatly faster it's just built specifically for qwen on MLX so provided an easier entry point for my optimisations)
- Patched MTPLX with:
  - Smarter MTP draft depth (going deeper when confidence is higher)
  - Reduced required synchronisation between the CPU & GPU

The smarter MTP draft depth enabled 4.3 tokens commited per verification run vs 3.2 with standard MTPLX.

[Originally posted on LinkedIn](https://www.linkedin.com/feed/update/urn:li:activity:7498257979578855424/)