G4

指南

Gemma 4 + Ollama 使用指南

使用 Ollama 运行 Gemma 4 的完整指南——安装、拉取模型、使用 REST API、通过 OpenAI SDK 集成 Python、创建自定义 Modelfile 等。

Ollama REST API OpenAI SDK Modelfile

1. 安装 Ollama

# Linux / macOS
curl -fsSL https://ollama.com/install.sh | sh

# macOS (Homebrew)
brew install ollama

# Windows: download .exe from ollama.com

安装后，Ollama 作为后台服务运行。使用以下命令验证： ollama --version.

2. 拉取 Gemma 4 模型

# Pull the default 31B model
ollama pull gemma4

# Pull specific variants
ollama pull gemma4:e4b    # Edge 4B — best for 8 GB VRAM
ollama pull gemma4:e2b    # Edge 2B — runs on 4 GB VRAM or CPU

# List downloaded models
ollama list

选择哪个版本

TagVRAMSpeed
gemma4:e2b~4 GBFastest
gemma4:e4b~6 GBFast
gemma4~18 GBBest quality

Ollama 使用 GGUF 量化模型（默认 Q4_K_M）。

3. 通过命令行运行

# Interactive chat in terminal
ollama run gemma4

# Single prompt (non-interactive)
ollama run gemma4 "Explain the MoE architecture in Gemma 4"

# With a custom system prompt
ollama run gemma4 --system "You are a Python expert." "Write a FastAPI hello world"

在交互模式下，输入 /bye to exit or /help to see commands.

4. REST API

Ollama 在以下地址提供 REST API： http://localhost:11434:

# The Ollama REST API runs at localhost:11434
# Generate completion
curl http://localhost:11434/api/generate -d '{
  "model": "gemma4",
  "prompt": "Why is Gemma 4 good for local deployment?",
  "stream": false
}'

# Chat completions
curl http://localhost:11434/api/chat -d '{
  "model": "gemma4",
  "messages": [
    {"role": "user", "content": "Hello!"}
  ]
}'

POST /api/generate

Single completion

POST /api/chat

Multi-turn conversation

GET /api/tags

List installed models

5. 与 OpenAI Python SDK 配合使用

Ollama 在以下地址支持 OpenAI API 格式： /v1/ — use your existing OpenAI code with zero changes:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:11434/v1",
    api_key="ollama"  # required but unused
)

response = client.chat.completions.create(
    model="gemma4",
    messages=[{"role": "user", "content": "What is Gemma 4?"}]
)
print(response.choices[0].message.content)

6. 流式响应

import requests
import json

response = requests.post(
    "http://localhost:11434/api/chat",
    json={
        "model": "gemma4",
        "messages": [{"role": "user", "content": "Tell me a story"}],
        "stream": True
    },
    stream=True
)

for line in response.iter_lines():
    if line:
        chunk = json.loads(line)
        print(chunk["message"]["content"], end="", flush=True)

7. 自定义 Modelfile

基于 Ollama 基础模型

# Create a Modelfile
FROM gemma4:e4b
SYSTEM "You are a helpful coding assistant specializing in Python."
PARAMETER temperature 0.7
PARAMETER top_p 0.9
# Build and run your custom model
ollama create mygemma -f Modelfile
ollama run mygemma

基于本地 GGUF 文件

# Use a local GGUF file
FROM /path/to/your/gemma4-q4_k_m.gguf
SYSTEM "You are a helpful assistant."

从 Hugging Face 上的社区仓库下载 GGUF 文件，例如 bartowski/google_gemma-4-E4B-it-GGUF。

技巧与常见问题

性能优化技巧

  • Set OLLAMA_NUM_GPU=1 to force GPU offloading
  • Use OLLAMA_NUM_PARALLEL=4 for concurrent requests
  • Keep context short — 2048 tokens is enough for most tasks
  • E4B with Q4_K_M is the best quality/speed ratio under 8 GB

在网络上暴露 Ollama

OLLAMA_HOST=0.0.0.0 ollama serve

然后从其他设备访问： http://<your-ip>:11434. Add authentication with a reverse proxy (nginx/Caddy) for production.

相关指南