Gemma 2 9B It
Jun 2024
Gemma 2 9B ItCompare inon
Benchmarks of Gemma 2 9B It20
BenchmarkByScoreRank
Knowledge1
Math1
Writing15
Legacy · saturated or no longer reported3
No benchmark matches
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Astraunstated×2.6+53,233%$10 / $50Monitoring can return HTTP 403+2OpenGemma 4 12Bunstated+53%+300%$0.10 / $0.30Memory (4-bit): 4.6 GB → 6 GB
BetterClaude Fable 5.1unstated×2.6+53,233%$10 / $50Replace forced tool_choice+5BetterClaude Opus 5unstated×2.5+26,567%$5 / $25BetterGPT-6 Solunstated×2.5+10,567%$2 / $10ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Astraunstated×2.6+53,233%$10 / $50Monitoring can return HTTP 403+2Claude Fable 5.1unstated×2.6+53,233%$10 / $50Replace forced tool_choice+5Claude Opus 5unstated×2.5+26,567%$5 / $25GPT-6 Solunstated×2.5+10,567%$2 / $10
Kimi K3unstatedOpen×2.5+15,900%$3 / $15Memory (4-bit): 4.6 GB → 1,668 GB+4ModelScoreCostPer taskWhat changes
Gemma 4 12BunstatedOpen+53%+300%$0.10 / $0.30Memory (4-bit): 4.6 GB → 6 GB
NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4Open+52%——Memory (4-bit): 4.6 GB → 11 GBrReka Flash 3unstatedOpen+46%+233%$0.10 / $0.20Memory (4-bit): 4.6 GB → 13 GBGemma 3 12BunstatedOpen+34%+67%$0.05 / $0.10Memory (4-bit): 4.6 GB → 6.1 GBGemma 3 4BunstatedOpen+27%+13%$0.04 / $0.05ModelScoreCostPer taskWhat changes
Gemini 3.8 Flashunstated×2.1—*$0.75 / $3.75Sampling parameters are ignored+1Gemini 3.6 Flashunstated+91%—*$0.75 / $3.75Gemini 3.5 Flash Liteunstated+85%—$0.30 / $2.50Gemini 3.1 Pro Previewunstated+77%—$2 / $12Cannot use both thinking controlsGemma 4 31BunstatedOpen+63%—$0.10 / $0.34Memory (4-bit): 4.6 GB → 19 GBGemma 4 26B A4BunstatedOpen+55%—$0.15 / $0.60Memory (4-bit): 4.6 GB → 15 GBGemma 4 12BunstatedOpen+53%—$0.10 / $0.30Memory (4-bit): 4.6 GB → 6 GBGemma 3 27BunstatedOpen+50%—$0.08 / $0.16Memory (4-bit): 4.6 GB → 16 GBAll Google models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · compressed✓ 16 GB · 8-bit✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceGemma termscommercial use with conditions
Benchmarks
all categoriesChat & Knowledge
Arena Text · overall1,267#171
Arena Text · Chinese1,184.9#163
Arena Text · English1,219.7#167
Arena Text · French1,190#135
Arena Text · German1,186.1#135
Arena Text · instruction following1,178#168
Arena Text · Japanese1,144.2#118
Arena Text · Korean1,136.7#131
Arena Text · non-English1,187.8#165
Arena Text · Russian1,200.4#162
Arena Text · Spanish1,200.2#140
EQ-Bench 3554.3#49
MATH Level 521#30
Arena Text · overall · full cohort1,207.4#165
GPQA Diamond · Epoch27.5#123
MMLU-Pro · official board52.1#15
OTIS Mock AIME 2024 20250.6#126
Writing & Language
Arena Text · creative writing1,259#155
EQ-Bench Creative Writing v3841.4#81
Arena Text · creative writing · full cohort1,205.4#158
FAQ
How much does Gemma 2 9B It cost?›
$0.03 per 1M input tokens and $0.06 per 1M output tokens (cheapest host: DeepInfra).
Is Gemma 2 9B It free to use?›
There is no free API; the cheapest paid price is $0.03 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Gemma 2 9B It, and what is it best at?›
#171 of 196 in Chat & Knowledge, #155 of 195 in Writing & Language.
Is Gemma 2 9B It better than Llama 4 Maverick?›
On EQ-Bench Creative Writing v3, Gemma 2 9B It scores 841.4 vs 860.1 — lower.
How can I use Gemma 2 9B It?›
Through the API of DeepInfra.
What is the context window of Gemma 2 9B It?›
8K tokens.
When was Gemma 2 9B It released? Is there a newer version?›
Released 2024-06-24. It is the current version in its line.
Is Gemma 2 9B It open source?›
Yes, the weights are open (gemma licence).
Can I run Gemma 2 9B It locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Gemma 2 9B It read images?›
No, it accepts text only.
What is Gemma 2 9B It?›
Gemma 2 9B It is an open-weights language model from Google, released Jun 2024.
What are the best alternatives to Gemma 2 9B It?›
GPT-6 Astra (better), Gemma 4 12B (open weights).