Mistral Large 3 675B-A41B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
PREVIEW — unverified. ~675B-total MoE with ~41B active per token, multimodal, Apache 2.0, 256K context. At Q4 it needs ~400 GB — an 8×80 GB server or equivalent. Apache 2.0 would make it one of the most permissive frontier-scale open weights if confirmed. Verify against the Hugging Face model card.
Mistral Large 3 675B-A41B 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。在 Apple Silicon 上，这部分来自统一内存。
按量化级别的显存与速度
计算基准：NVIDIA RTX 4090 (24 GB)。仅含权重与开销：该模型架构未公开，因此未计入 KV 缓存。
| 量化 | 显存 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 222.7 GB | — | 放不下 | |
| Q3_K_M 3.41 bpw | 288.5 GB | — | 放不下 | |
| Q4_K_M 4.83 bpw | 408.3 GB | — | 放不下 | |
| Q5_K_M 5.67 bpw | 479.2 GB | — | 放不下 | |
| Q6_K 6.56 bpw | 554.3 GB | — | 放不下 | |
| Q8_0 8.50 bpw | 718 GB | — | 放不下 | |
| F16 16.00 bpw | 1350.8 GB | — | 放不下 |
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. Mistral Large 3 675B-A41B 显存计算器 →
运行 Mistral Large 3 675B-A41B
Mistral Large 3 675B-A41B is not practical on a single consumer GPU: it needs about 408.3 GB at Q4_K_M, more than any single device in our catalogue holds with headroom. How multi-GPU inference works, or rent a multi-GPU server by the hour:
如何运行 Mistral Large 3 675B-A41B
安装 Ollama，然后运行：
ollama run mistral-large-3规格
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- 参数量
- 675 Billion (41B active)
- 上下文窗口
- 256,000
- 架构
- Mixture-of-Experts (multimodal)
- 提供商
- Mistral AI
- 许可证
- Apache 2.0
- Practical deployment
- Multi-GPU server
- 规格量化
- Q4_K_M
- 系统内存
- 1024 GB
- 记录更新于
- 2026-06-26
Commercial use permitted. No usage restrictions beyond attribution.
限制与注意事项
- Mistral's API retires this model on 30 April 2027; the weights stay downloadable. Successor: Mistral Large 4.
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。
我的 GPU 能运行 Mistral Large 3 675B-A41B 吗？
Mistral Large 3 675B-A41B — 常见问题
How much VRAM does Mistral Large 3 675B-A41B need?
About 408 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 Mistral Large 3 675B-A41B run on an RTX 4090 (24 GB)?
No. Mistral Large 3 675B-A41B needs about 408 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Mistral Large 3 675B-A41B locally?
Install Ollama and run `ollama run mistral-large-3`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.