Mistral Medium 3.5 128B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
127.7B 稠密参数，88 层，分组查询注意力 8 个 KV 头，上下文 262,144 token，支持图像输入。以 FP8 发布（磁盘占用 267 GB）；Mistral 推荐 vLLM，并为 llama.cpp 指向 Unsloth 的 GGUF，Ollama 也提供 128B 标签。它的 Modified MIT 许可证并非仅要求署名的那种：合并月收入超过 2000 万美元的公司不获得任何权利。
Mistral Medium 3.5 128B 在 Q4_K_M 下约需 78 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)。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 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 45.7 GB | ~3 tok/s | 需卸载 | |
| Q3_K_M 3.41 bpw | 58.2 GB | — | 放不下 | |
| Q4_K_M 4.83 bpw | 80.9 GB | — | 放不下 | |
| Q5_K_M 5.67 bpw | 94.3 GB | — | 放不下 | |
| Q6_K 6.56 bpw | 108.5 GB | — | 放不下 | |
| Q8_0 8.50 bpw | 139.4 GB | — | 放不下 | |
| F16 16.00 bpw | 259.2 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 Medium 3.5 128B 显存计算器 →
运行 Mistral Medium 3.5 128B
目录中能运行 Mistral Medium 3.5 128B 的最便宜 GPU 是 NVIDIA DGX Spark (128 GB).
或在 Vast.ai 比较，低至 $0.77/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。
如何运行 Mistral Medium 3.5 128B
安装 Ollama，然后运行：
ollama run mistral-medium-3.5:128b规格
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- 参数量
- 127.7 Billion
- 上下文窗口
- 262,144
- 架构
- Dense Transformer (GQA) with vision encoder
- 提供商
- Mistral AI
- 许可证
- Modified MIT (revenue-gated)
- Availability
- Weights downloadable
- Practical deployment
- Workstation (large unified memory or pro GPU)
- 规格量化
- Q4_K_M
- 系统内存
- 128 GB
- 记录更新于
- 2026-10-15
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
No rights at all for a company whose consolidated monthly revenue exceeds $20M.
限制与注意事项
- Licence: no rights at all for a company above $20M consolidated monthly revenue.
- Dense 128B: every token reads all 128B parameters, so decode is far slower than a mixture-of-experts model of similar size; the estimate table on this page gives the figure for your hardware.
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。
Mistral Medium 3.5 128B — 常见问题
How much VRAM does Mistral Medium 3.5 128B need?
About 78 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 Medium 3.5 128B run on an RTX 4090 (24 GB)?
No. Mistral Medium 3.5 128B needs about 78 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 Medium 3.5 128B locally?
Install Ollama and run `ollama run mistral-medium-3.5:128b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.