Google DeepMindopen-weight
Released: 2024-06-27Gemma 2 9B
Best-in-class single-GPU open weights model outperforming original Llama 2 70B across major academic benchmarks.
Intelligence Index
71.0/ 100
Calibrated multi-domain compositeThroughput Speed
130tok/sec
Output streaming throughputTime To First Token
220ms
Initial chunk server latencyLiveBench Contam-Free
66.8%
September 2026 suite scoreLiveBench Multi-Domain Evaluation Breakdown
Monthly refreshed contamination-free test setsLogical Reasoning69.0%
Coding & Repo Repair64.0%
Mathematics (AIME)68.0%
Data Analysis & Tables65.5%
Language & Comprehension67.0%
Instruction Following67.5%
Sourced Benchmark Evaluations (3)
Verified performance across authoritative benchmarks with provenance tracking.Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run gemma-2-9b
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "gemma-2-9b",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for Gemma 2 9B represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.