Gemma 4 (Withdrawn Listings) — Google DeepMind 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Google DeepMind's breakthrough open-weight model. Gemma 4 27B delivers GPT-4 level performance at 14 GB VRAM, making frontier-quality AI accessible on consumer GPUs. Features a hybrid architecture with interleaved local and global attention, multi-image understanding, and 128k context window. Achieves 85 tokens/second on RTX 4090.
变体
Gemma 4 (Withdrawn Listings) 最小的变体在 Q4_K_M 下约需 3 GB 显存——量化权重加框架开销，不含 KV 缓存。
| 模型 | Q4 下显存 | 显存 | 上下文 | 运行 |
|---|---|---|---|---|
| Gemma 4 4B 4B | ~3.2 GB | 128,000 | ollama run gemma4:4b | |
| Gemma 4 12B 12B | ~8 GB | 128,000 | ollama run gemma-4-legacy | |
| Gemma 4 27B ⭐ 27B | ~17.1 GB | 128,000 | ollama run gemma4:27b |
显存为 Q4_K_M 下的量化权重加开销，与 GPU 与显存检测器使用同一引擎计算。
如何在本地运行 Gemma 4 (Withdrawn Listings)
安装 Ollama，然后拉取标签。
ollama run gemma4:4b在上方选择一个尺寸，查看它自己的显存、速度估算和安装命令。
许可证
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
适用于: Gemma 4 4B, Gemma 4 12B, Gemma 4 27B ⭐推荐 GPU
目录中能在本地运行 Gemma 4 (Withdrawn Listings)（至少 3 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
Gemma 4 (Withdrawn Listings) — 常见问题
How much VRAM does Gemma 4 (Withdrawn Listings) need?
Gemma 4 (Withdrawn Listings) needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Gemma 4 4B (3 GB, Q4_K_M); Gemma 4 12B (8 GB, Q4_K_M); Gemma 4 27B ⭐ (17 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Gemma 4 (Withdrawn Listings) on an RTX 4090 (24 GB)?
Yes — Gemma 4 (Withdrawn Listings) runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Gemma 4 (Withdrawn Listings)?
Q4_K_M is the best balance of quality and VRAM for Gemma 4 (Withdrawn Listings) in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Gemma 4 (Withdrawn Listings) with Ollama?
Install Ollama, then run: ollama run gemma4:4b. This downloads Gemma 4 (Withdrawn Listings) and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.