Will It Run AI

GoogleGoogle

Gemma 2 9B

当前
huggingfaceHuggingFaceollamaOllama
380.9K下载量811点赞Jun 2024发布日期8K tokens上下文Gemma许可证36 基础质量

Gemma 2 9B (9B parameters) requires approximately 12.4 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 15 GB of VRAM.

快速开始

— 复制粘贴即可本地运行

Copy-paste commands to run Gemma 2 9B on your machine.

Run

ollama run gemma2

Quick specs

Parameters9B
Architecturedense
Context8K tokens
Modalitytext
Min RAM3.5 GB
Rec. RAM5.5 GB (Q4_K_M)
LicenseGemma
FamilyGemma
✓ Chat

About this model

Gemma 2 9B is Google's mid-size open model built on Gemini research. Features improved reasoning and safety with a novel architecture optimized for efficient inference on consumer hardware.

相关模型

你的硬件

检测中...

快速推荐

最佳性价比B
RX 7600 XT 16GB~$329 — 24 tok/s
最佳综合A
RX 7900 XT 20GB~$899 — 92 tok/s

最佳硬件

Gemma 2 9B 的最佳选择

NVIDIA
RTX 5080 Laptop 16GBA
16 GB
RX 7900 XT 20GBA
20 GB
NVIDIA
RTX A4500 20GBA
20 GB
NVIDIA
RTX 4080 Super 16GBA
16 GB
NVIDIA
RTX 5080 16GBA
16 GB

运行此模型

Gemma 2 9B on RTX 5080 Laptop 16GBGemma 2 9B on RX 7900 XT 20GBGemma 2 9B on RTX A4500 20GB

量化选项

各量化级别的 VRAM 估算

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
3.5 GB
Low—
Q3_K_S
3
4.4 GB
Low—
NVFP4
4
5.0 GB
Medium—
Q4_K_M
4
5.5 GB
Medium—
Q5_K_M
5
6.5 GB
High—
Q6_K
6
7.4 GB
High—
Q8_0
8
9.6 GB
Very High—
F16
16
18.5 GB
Maximum—

Quality benchmarks

Gemma 2 9B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—
HumanEval+64.0%
Aider Polyglot—
LiveCodeBench—

Reasoning

MMLU-Pro47.7%
GPQA Diamond14.8%
MATH-50036.6%
ARC Challenge68.4%

General

Chatbot Arena—
IFEval73.6%

Source: official · 2024-06-27

硬件兼容性

全部硬件的适配估算

打开计算器

Computing compatibility...

内存详细分析

Reference: RTX 2060 6GB

Weights5.5 GB
KV Cache5.1 GB
Runtime1.2 GB
Headroom0.6 GB

常见问题

FAQ — Gemma 2 9B

另请参阅

量化指南评分方法打开计算器