oQe Models Updated with Improved Quantization, Lower KL Divergence

Key Info

All oQe models have been updated with Improved oQe Quantization, available from oMLX 0.7.1. Compared with previous oQe builds, KL divergence is 11.6–18.1% lower on code and 10.2–13.8% lower on prose.

Highlights

• Qwen3.8-27B oQ4e: code KL 0.0143 → 0.0117 (-18.1%), prose 0.0696 → 0.0600 (-13.8%)
• Qwen3.8-Flash-Next oQ4e: code KL 0.0877 → 0.0776 (-11.6%), prose 0.1909 → 0.1713 (-10.2%)
• Below oQ4, the Engram and N-gram tables stay at 4 bits and are left out of the bit budget
• oMLX can serve these tables from SSD instead of memory