GLM-5.3 hits 310 tok/s on Databricks inference, claimed strongest OSS coding model
jeremyphoward · x · 2026-09-03
A Databricks-affiliated post reports GLM-5.3 running at 310 tok/s on Databricks inference, ranking #1 in both speed and latency. On their internal coding benchmark, GLM-5.3 is the strongest open-source coding model, competitive with Fable 5 and Opus 4.8. Jeremy Howard replied asking how to use it.
Note: these are vendor-side claims based on an internal benchmark, not independently verified.
More from Infra
- ClickHouse aggregates 100B rows in 0.4s with parallel replicas auto-scaling — Abhishekcur · 2026-10-18
- Auction-based LLM routing paper finds fixed token pricing wastes 10%-71% in costs — _onionesque · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- SGLang Summit sponsors jump from 11 to 36 in one week — ying11231 · 2026-10-18
- Oracle CDS hits record 300bps, called first AI trade domino after Barclays sell downgrade — arthurcolle · 2026-10-18
- Agent Coding Workflow Would Cost ~$40k/Month on API Pricing, Dev Reveals — ChrisRackauckas · 2026-10-18