3 Ways to Prompt Open Models Like Llama and gpt-oss Directly in BigQuery SQL
rseroter · x · 2026-10-23
A walkthrough of calling open-weight models (Gemma, Llama 4, gpt-oss, Mistral Small, HF models) on massive BigQuery tables with a few lines of SQL and zero data movement. Three paths: built-in embeddinggemma-300m via AI.EMBED on BigQuery Slots; serverless MaaS endpoints billed per token; and self-deployed Model Garden/Hugging Face endpoints billed per GPU hour — with auto batching, retries, and SQL-managed endpoints built in.
More from coding & agent
- We tested 12 LLM classifiers — the new classifier hype is LARP — KlausCodes · 2026-10-23
- Dev builds ESP32 desk display showing Claude Code and Codex agent status via local Go helper — tonylook · 2026-10-23
- Let your agent read its own traces: AgentsView + history tool debugging workflow — dbreunig · 2026-10-23
- YC-backed Mireye launches land search API + MCP with 160M parcels for AI agents — ycombinator · 2026-10-23
- Testing 12 decision systems: the new LARP hype around classifiers — KlausCodes · 2026-10-23
- Monid launches 'Product Hunt for agents,' ranking tools by real agent calls — claudeai · 2026-10-23