Hacker News front pageSep 17, 2026, 02:50 UTC+8

Training a 4B model to produce 81% faster query plans than Postgres

Rohan Bansal post-trained a Qwen 4B model to beat Postgres's default query plans. After SFT distillation from 500 GPT-6 Astra trajectories and a custom GRPO variant for RL, the model achieved 44.7% latency reduction and 81% geometric mean speedup across 113 join-heavy queries. Training ran on a rented 2×H100 node with four Postgres containers on his desk for measurement. The post doesn't disclose total training time or per-inference latency.

Why it matters: A 4B model trained via RL beats Postgres default plans by 81% on the Join Order Benchmark. The method is practically interesting, but only 113 queries were tested—generalization is unproven, capping the score at 78.

Read the original ↗Export Markdown

Take

The numbers are eye-catching: 81% geometric mean speedup, 44.7% latency reduction. The approach: SFT on 500 trajectories from GPT-6 Astra, then a custom GRPO variant where the model generates plans, runs them on real Postgres, and gets rewarded by actual execution time. Training on rented 2×H100, four Postgres containers on the author's desk for measurement.

I'd discount this a bit. Only 113 join-heavy queries tested—no point queries, aggregations, or subqueries. The post doesn't disclose per-inference latency for the 4B model itself. If plan generation takes longer than execution, the speedup is meaningless. Also, Postgres defaults aren't the ceiling; no comparison against pg_hint_plan or manual tuning.

A fairer read: this shows RL can teach a small model to exploit Postgres optimizer blind spots on specific query patterns. If inference latency is manageable, it might help with fixed-pattern complex reports. But it's a blog post with no code or reproduction yet—treat it as an interesting direction.

Source: Hacker News front page · rohanbansal.com
Published: Sep 17, 2026, 02:50 UTC+8 · 13 days ago