Mistral Large 3 — Mistral AI 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Mistral's open-weight flagship, released 2 December 2025: a 675B MoE with 41B active parameters, Apache-2.0, 256K context. Datacentre-scale to self-host; most readers will rent it.
变体
Mistral Large 3 最小的变体在 Q4_K_M 下约需 408 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 |
|---|---|---|---|---|
| Mistral Large 3 675B-A41B → 675B (41B active) | ~408.3 GB | 256,000 | ollama run mistral-large-3 |
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 Mistral Large 3
安装 Ollama，然后拉取标签。
ollama run mistral-large-3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
Commercial use permitted. No usage restrictions beyond attribution.
适用于: Mistral Large 3 675B-A41B我的 GPU 能运行 Mistral Large 3 吗？
Mistral Large 3 — 常见问题
How much VRAM does Mistral Large 3 need?
Mistral Large 3 needs about 408 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Mistral Large 3 675B-A41B (408 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Mistral Large 3 on an RTX 4090 (24 GB)?
Mistral Large 3's smallest variant needs about 408 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for Mistral Large 3?
Q4_K_M is the best balance of quality and VRAM for Mistral Large 3 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 Mistral Large 3 with Ollama?
Mistral Large 3 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.