Google9BQ4_K_M 下约 6 GB 显存

Gemma 2 9B IT — 显存、速度与本地部署

作者: Jakub Rusinowski · 最后更新:

Punchy and creative. Excellent for creative writing and brainstorming.

Gemma 2 9B IT 在 Q4_K_M 下约需 6 GB 显存——量化权重加框架开销,不含 KV 缓存。在 Apple Silicon 上,这部分来自统一内存。

逻辑88
创意95
编程80

按量化级别的显存与速度

计算基准:NVIDIA RTX 4090 (24 GB)。包含 8K 上下文的 KV 缓存,因此数值高于上方的主数字。

量化显存速度(估算)适配
Q2_K
2.63 bpw
6.6 GB~125 tok/s可运行
Q3_K_M
3.41 bpw
7.5 GB~109 tok/s可运行
Q4_K_M
4.83 bpw
9.1 GB~89 tok/s可运行
Q5_K_M
5.67 bpw
10 GB~80 tok/s可运行
Q6_K
6.56 bpw
11 GB~72 tok/s可运行
Q8_0
8.50 bpw
13.2 GB~60 tok/s可运行
F16
16.00 bpw
21.6 GB~36 tok/s勉强

黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型,详见 方法说明页. Gemma 2 9B IT 显存计算器 →

运行 Gemma 2 9B IT

目录中能运行 Gemma 2 9B IT 的最便宜 GPU 是 Intel Arc B570 (10 GB).

购买此硬件 Intel Arc B570 10GB — 10 GB VRAM · 150 W board power立即云端部署 RunPod 上的 RTX 4090 — 低至 $0.34/小时 · 价格核实于 2026-07

或在 Vast.ai 比较,低至 $0.35/小时 (typical low · varies)

作为亚马逊联盟成员,我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金,您无需额外付费。

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买,LLM Configurator 可能会获得佣金,而你无需支付任何额外费用。作为亚马逊联盟成员(Amazon Associate),LLM Configurator 会从符合条件的购买中获得收益。
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026年价格波动较大——请以当前商品页价格为准。

如何运行 Gemma 2 9B IT

安装 Ollama,然后运行:

ollama run gemma2
Hugging Face 上的权重: google/gemma-2-9b-it ↗

Download Gemma 2 9B IT — GGUF Quantizations

Pick a quantization and open it in LM Studio, Ollama, or Jan, or download the raw .gguf file directly. Quant list and sizes resolved from Hugging Face.

Gemma 2 9B IT — GGUF quants · bartowski/gemma-2-9b-it-GGUF

QuantSizeDownload (.gguf)
Q3_K_M3.84 GB (est.)gemma-2-9b-it-Q3_K_M.gguf
Q4_K_M5.43 GB (est.)gemma-2-9b-it-Q4_K_M.gguf
Q5_K_M6.38 GB (est.)gemma-2-9b-it-Q5_K_M.gguf
Q6_K7.38 GB (est.)gemma-2-9b-it-Q6_K.gguf
Q8_09.56 GB (est.)gemma-2-9b-it-Q8_0.gguf

Download in LM Studio: lms get bartowski/gemma-2-9b-it-GGUF

Want this model on your phone? You can run it on your desktop with LM Studio and chat from your iPhone or iPad over an encrypted link — see Run LM Studio Models on Your Phone (LM Link).

规格

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

参数量
9 Billion
上下文窗口
8,192
架构
Dense Transformer
提供商
Google
许可证
Gemma Terms
规格量化
Q4_K_M
系统内存
16 GB
记录更新于
2024-06-27
许可证Gemma Terms允许商业使用

Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

质量与使用场景

评分由模型作者或独立评测方发布——衡量质量而非吞吐量,并非我们实测。

最适合creativechat

我的 GPU 能运行 Gemma 2 9B IT 吗?

Gemma 2 9B IT — 常见问题

How much VRAM does Gemma 2 9B IT need?

About 6 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Gemma 2 9B IT run on an RTX 4090 (24 GB)?

Yes. Gemma 2 9B IT needs about 6 GB at Q4_K_M, inside a 24 GB card, at an estimated 89 tokens/sec.

How do I run Gemma 2 9B IT locally?

Install Ollama and run `ollama run gemma2`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.