Key Specifications

SpecificationGemma 2 27BGemma 2 9B
Vendorgooglegoogle
Versiongemma-2-27bgemma-2-9b
Release Date2024-06-272024-06-27
Context Window8192 tokens8192 tokens
Input Modalitiestexttext
Output Modalitiestexttext
LicenseGemma LicenseGemma License
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkGemma 2 27BGemma 2 9BWinner
ARC93.190.3Gemma 2 27B
BBH71.266.7Gemma 2 27B
GPQA35.430.3Gemma 2 27B
GSM8K77.464.3Gemma 2 27B
HUMANEVAL72.460.9Gemma 2 27B
IFEVAL72.564.3Gemma 2 27B
MATH35.528.9Gemma 2 27B
MMLU77.464.3Gemma 2 27B
MUSR5344.1Gemma 2 27B
WINOGRANDE80.572.5Gemma 2 27B

Pricing Comparison

Tier (per Mtok)Gemma 2 27BGemma 2 9B
Input$0.7$0.3
Output$0.7$0.3
Cache Read$0$0
Cache Write$0$0

Gemma 2 27B mot Gemma 2 9B

Modellöversikt

Gemma 2 27B and Gemma 2 9B are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Nyckelspecifikationer

LeverantörReleasedatumKontextfönsterLicens
Google / Google2024-06-27 / 2024-06-278K / 8KGemma License / Gemma License

Benchmarkprestanda

BenchmarkGemma 2 27BGemma 2 9BVinnare
ARC93.190.3A
BBH (BIG-Bench Hard)71.266.7A
GPQA35.430.3A
GSM8K (Grade School Math 8K)77.464.3A
HumanEval72.460.9A
IFEval72.564.3A
MATH35.528.9A
MMLU (Massive Multitask Language Understanding)77.464.3A
MUSR53.044.1A
WinoGrande80.572.5A

Prisjämförelse

InmatningUtmatningCacheläsningCacheskrivning
— / —— / —— / —— / —

per miljon tokens — A / B

Styrkor & Svagheter

Gemma 2 27B

  • ✅ 可靠的通用模型。
  • ⚠️ 闭源专有模型,不支持自托管。
  • ⚠️ 上下文窗口 8K 偏小。

Gemma 2 9B

  • ✅ 可靠的通用模型。
  • ⚠️ 闭源专有模型,不支持自托管。
  • ⚠️ 上下文窗口 8K 偏小。

Redaktörens åsikt

Gemma 2 27B and Gemma 2 9B each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

Vanliga frågor

Which model is better for coding tasks?

Refer to the HumanEval benchmark table; the model with a higher score is better suited for coding tasks.

Which model is cheaper?

Refer to the pricing comparison table above; the model with lower input/output prices is more cost-effective.

Which has a longer context window?

Refer to the key specifications table; the model with a larger context window is better for long documents.

Referenser

Editor's Take

See Editor's Take section.