Gemma 2 9B Instruct

Find hardware that runs Gemma 2 9B Instruct on your budget

Reference: Model card on Hugging Face · Published benchmark scores

Parameters: 9.24 B
Active per token: 9.24 B
Architecture: Dense
Modality: text
Max context: 8192
Released: 2024-06-24
License: gemma

Measurements

Decode is token generation — the speed you feel while an answer streams. Prefill is prompt processing — the wait before it starts. Why bandwidth predicts decode speed.

What verified, single-source and estimated mean, and the same rows with every filter and sort in the benchmarks explorer.

Speed over time

Cheapest hardware by target speed

The lowest-priced entry that reaches each threshold, using the strongest evidence available. Estimated rows are marked.