Gemma 3n vs Gemma 3
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Google 的 Gemma 3n 与 Google 的 Gemma 3 是当前备受关注的两款主力 AI 模型。Gemma 3n 提供 32K Token 上下文窗口，API 定价为每百万 Token 输入 $0.00 / 输出 $0.00；而 Gemma 3 提供 131.1K Token 上下文窗口，定价为每百万 Token 输入 $0.00 / 输出 $0.00。以下为两者的基准测试、延迟与成本全面对比。
切换并对比任意模型
Select any AI models from our verified benchmark database to generate live side-by-side matrices.
Gemma 3n
原生语音与音频大模型Google 推出的 Gemma 3n 是一款专注于超自然语音合成、实时音频理解与低延迟语音交互的大模型，具备 32K 上下文窗口、150 Token/秒生成速度与 52/100 综合智能指数（免费开源权重）。
$0.00 / 1M
$0.00 / 1M
32K tokens
N/A
Gemma 3
原生多模态视觉模型Google 推出的 Gemma 3 是一款原生支持图文多模态理解、视觉图表解析与跨模态推理的大模型，具备 131K 上下文窗口、105 Token/秒生成速度与 68/100 综合智能指数（免费开源权重）。
$0.00 / 1M
$0.00 / 1M
131.1K tokens
N/A
核心差异一览
- Both models cost the same under this workload — choose on capability, not price.
- Gemma 3 has a larger context window (131K vs 32K tokens).
- Gemma 3n is faster at 150 tok/s vs 105 tok/s.
| Feature | Gemma 3n | Gemma 3 |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 52 | 68 |
Provider | ||
Input Price Cost per million input tokens | $0.00 / 1M | $0.00 / 1M |
Output Price Cost per million output tokens | $0.00 / 1M | $0.00 / 1M |
Blended Price Weighted 7:2:1 cache:input:output per 1M | $0.00 / 1M | $0.00 / 1M |
Context Window Maximum input + output tokens | 32K tokens~48 A4 pages of text | 131.1K tokens~197 A4 pages of text |
Max Output Tokens Per single request | 4K | 16K |
Throughput Speed Tokens generated per second | 150 tok/s | 105 tok/s |
SWE-bench Verified Real-world software engineering | N/A | N/A |
GPQA Diamond Graduate-level reasoning | N/A | 61% |
各项指标谁更胜一筹？
At-a-glance decision frameworkEvaluations ongoing
权威基准测试得分对比
Official evaluation metrics verified by independent third-party research labs.
Challenging questions created by domain experts to test complex PhD-level reasoning.
Hardened reasoning and academic knowledge benchmark with reduced lucky-guess probability.
Crowdsourced human preference evaluation based on blind, head-to-head model battles.
Tokens emitted per second during active generation streaming.
延迟与响应速度
Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.
实时 Token 成本模拟器
Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.
Gemma 3n · Strengths & Key Advantages
- 提供 32K 上下文窗口与最高 4K 输出容量，核心基准表现优异（MMLU-Pro 64% · Arena Elo 1220）
- 高达 150 Token/秒的生成吞吐量，首字延迟 (TTFT) 仅约 220 毫秒
- 开放模型权重 (2B / 5B)，支持通过 vLLM、SGLang 或 Ollama 在私有 GPU 集群上本地部署与微调
Considerations & Trade-offs
- 在本地以满血精度运行需要较高的 GPU 显存 (VRAM) 与运维基础设施
- 在超长链路的前沿科研推导任务上，深度略逊于顶配重型旗舰推理模型
Gemma 3 · Strengths & Key Advantages
- 提供 131K 上下文窗口与最高 16K 输出容量，核心基准表现优异（GPQA Diamond 61% · MMLU-Pro 78%）
- 高达 105 Token/秒的生成吞吐量，首字延迟 (TTFT) 仅约 320 毫秒
- 开放模型权重 (1B / 4B / 12B / 27B)，支持通过 vLLM、SGLang 或 Ollama 在私有 GPU 集群上本地部署与微调
Considerations & Trade-offs
- 在本地以满血精度运行需要较高的 GPU 显存 (VRAM) 与运维基础设施
- 在超长链路的前沿科研推导任务上，深度略逊于顶配重型旗舰推理模型
Token Use & Task Economics
Estimated cost and token consumption to complete one representative agentic task.
| Metric | Gemma 3n | Gemma 3 |
|---|---|---|
Cost per Task Estimated USD to finish one task | $0.00 | $0.00 |
Output Tokens / Task Tokens generated per task | 3K | 5K |
Reasoning Tokens / Task Thinking tokens burned per task | 0K | 0K |
技术规格参数
Architecture, release timeline, capabilities, and modalities.
| Feature | Gemma 3n | Gemma 3 |
|---|---|---|
| Official API Model ID (SDK) | models/gemma-3n | models/gemma-3 |
| API Protocol | Google Gemini API (generateContent) + OpenAI-Compatible SDK | Google Gemini API (generateContent) + OpenAI-Compatible SDK |
| Release Date | 2025-06 | 2025-03 |
| Knowledge Cutoff | March 2025 | December 2024 |
| Architecture | Edge-optimized multimodal transformer with audio support | Native multimodal open transformer with expanded context |
| Parameters | 2B / 5B | 1B / 4B / 12B / 27B |
| Enterprise Rate Limits (RPM / TPM) | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud |
| Long-Context Tier (>128K/200K) | Free across full context window (only KV-cache VRAM scales) | Free across full context window (only KV-cache VRAM scales) |
| Prompt Cache Policy & TTL | Automatic prefix KV-caching in vLLM / SGLang (0 cost) | Automatic prefix KV-caching in vLLM / SGLang (0 cost) |
| Computer Use / GUI Agent | Supported (Screen coordinate grounding, browser & desktop GUI action loops) | Supported (Screen coordinate grounding, browser & desktop GUI action loops) |
| MCP & Parallel Tool Calling | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema |
| Web Search Grounding & Sandbox | Built-in Google Search Grounding + Managed Python Code Execution Sandbox | Built-in Google Search Grounding + Managed Python Code Execution Sandbox |
| Official Fine-Tuning Support | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) |
| Multimodal Token Billing | Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) · Audio (~25–32 tokens/sec) | Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) |
| Quantization & Min GPU VRAM | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 2 GB VRAM (4-bit Quantized) · 4 GB VRAM (Native BF16) | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 2 GB VRAM (4-bit Quantized) · 4 GB VRAM (Native BF16) |
| Safety & Frontier Classification | Google DeepMind Frontier Safety Framework Verified | Google DeepMind Frontier Safety Framework Verified |
| Enterprise Compliance (ZDR/HIPAA/SOC2) | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control |
| Input Modalities | text, vision, audio | text, vision |
| Output Modalities | text | text |
Gemma 3n vs Gemma 3: 常见问题解答 (FAQ)
Which is more intelligent, Gemma 3n or Gemma 3?
Gemma 3 is more intelligent. It scores 68 compared with 52 on the composite Intelligence Index.
Which model is faster?
Gemma 3n is faster, generating 150 tokens per second compared with 105 tokens per second.
Which model has lower latency?
Gemma 3n has lower latency, with a time to first token of 0.22s compared with 0.32s.
Which model has a larger context window?
Gemma 3 has a larger context window, supporting 131.1K tokens compared with 32K tokens.
综合结论
综合来看，Gemma 3n（适合：专注于超自然语音合成、实时音频理解与低延迟语音交互的任务、企业级 RAG 检索增强生成、自动化智能体工作流与高可靠 API 集成。）与 Gemma 3（适合：原生支持图文多模态理解、视觉图表解析与跨模态推理的任务、企业级 RAG 检索增强生成、自动化智能体工作流与高可靠 API 集成。）各具优势：Gemma 3 在综合智能与编程基准测试中表现更强，Gemma 3n 拥有更快的 Token 生成速度，而 Gemma 3n 则在规模化 API 部署中具备更高的成本效益。
常见问题 (FAQ)
在编程和深度推理方面，Gemma 3n 和 Gemma 3 哪个更强？+
在综合智能指数与编程基准评测中，Gemma 3 表现占优。建议结合上方的 SWE-bench Verified 与 GPQA Diamond 跑分根据具体场景选择。
Gemma 3n 与 Gemma 3 的 API 价格哪个更便宜？+
Gemma 3n 的 API 价格为输入 $0.00 / 输出 $0.00（每百万 Token），Gemma 3 为输入 $0.00 / 输出 $0.00。综合混合成本来看，Gemma 3n 更具性价比。
哪款模型拥有更大的上下文窗口和更快的响应速度？+
Gemma 3n 支持 32K Token 上下文窗口，而 Gemma 3 支持 131.1K Token。在流式生成速度方面，Gemma 3n 的吞吐表现更快。
Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.
Related reading
- Command A Vision vs Gemma 3n：基准测试、API 价格与速度全面对比 (2026)对比
- Gemma 3 vs Gemma 2：基准测试、API 价格与速度全面对比 (2026)对比
- Gemma 3 vs Llama 4 Scout：基准测试、API 价格与速度全面对比 (2026)对比
- Aion-3.0 vs Aion-Mini：基准测试、API 价格与速度全面对比 (2026)对比
- Aion-3.0 vs Gemini 3.6 Flash：基准测试、API 价格与速度全面对比 (2026)对比
- Aion-Mini vs Laguna XS 2.1：基准测试、API 价格与速度全面对比 (2026)对比
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
数据来源: Google 与 Google 官方 API 文档、模型发布说明及独立基准测试报告 (2026)。