Will It Run AI

GoogleGoogle

Gemma 2 27B

当前
133.6K下载量567点赞Jun 2024发布日期8K tokens上下文Gemma许可证48 基础质量

Gemma 2 27B (27B parameters) requires approximately 29.5 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 34 GB of VRAM.

快速开始

— 复制粘贴即可本地运行

Copy-paste commands to run Gemma 2 27B on your machine.

Run

ollama run gemma2:27b

Quick specs

Parameters27B
Architecturedense
Context8K tokens
Modalitytext
Min RAM10.5 GB
Rec. RAM16.5 GB (Q4_K_M)
LicenseGemma
FamilyGemma
Chat Reasoning

About this model

Gemma 2 27B 是 Google 最大的 Gemma 2 模型,在同等规模的开放模型中性能处于领先地位。基于 Gemini 技术构建,具备强大的推理、代码和多语言能力。

相关模型

你的硬件

检测中...

快速推荐

最佳硬件

Gemma 2 27B 的最佳选择

运行此模型

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
10.5 GB
Low
Q3_K_S
3
13.2 GB
Low
NVFP4
4
15.1 GB
Medium
Q4_K_M
4
16.5 GB
Medium
Q5_K_M
5
19.4 GB
High
Q6_K
6
22.1 GB
High
Q8_0
8
28.9 GB
Very High
F16
16
55.4 GB
Maximum

Quality benchmarks

Gemma 2 27B benchmark scores

Benchmark verified

Coding

SWE-bench Verified
HumanEval+71.3%
Aider Polyglot
LiveCodeBench

Reasoning

MMLU-Pro57.5%
GPQA Diamond16.7%
MATH-50050.1%
ARC Challenge71.4%

General

Chatbot Arena
IFEval79.0%

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

Weights16.5 GB
KV Cache11.2 GB
Runtime1.2 GB
Headroom0.6 GB

常见问题

FAQ — Gemma 2 27B

另请参阅