MiniMax230BQ4_K_M 下约 140 GB 显存

MiniMax M2.5 230B — 显存、速度与本地部署

作者: Jakub Rusinowski · 最后更新:

230B MoE model with 80.2% SWE-bench score — surpassing Claude Opus 4.6 on that benchmark at a fraction of the cost ($0.30/$0.56 per 1M tokens vs Claude's $15/$75). Supports 1M token context and multimodal input. Needs ~130 GB at Q4 — accessible via Mac Studio 192 GB or 2-4× A100 cluster.

MiniMax M2.5 230B 在 Q4_K_M 下约需 140 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。

逻辑93
创意90
编程95

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。

量化显存速度(估算)适配
Q2_K
2.63 bpw
76.4 GB—放不下
Q3_K_M
3.41 bpw
98.8 GB—放不下
Q4_K_M
4.83 bpw
139.6 GB—放不下
Q5_K_M
5.67 bpw
163.7 GB—放不下
Q6_K
6.56 bpw
189.3 GB—放不下
Q8_0
8.50 bpw
245.1 GB—放不下
F16
16.00 bpw
460.6 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. MiniMax M2.5 230B 显存计算器 →

运行 MiniMax M2.5 230B

目录中能运行 MiniMax M2.5 230B 的最便宜 GPU 是 Apple M2 Ultra (192 GB).

购买此硬件 Apple Mac Studio M2 Ultra — 192 GB VRAM · 60 W board power立即云端部署 RunPod

或在 Vast.ai 比较

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。

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买,LLM Configurator 可能会获得佣金,而你无需支付任何额外费用。作为亚马逊联盟成员(Amazon Associate),LLM Configurator 会从符合条件的购买中获得收益。
Apple Mac Studio M2 Ultra
192 GB VRAM · 60 W board power
2026年价格波动较大——请以当前商品页价格为准。

如何运行 MiniMax M2.5 230B

安装 Ollama,然后运行:

ollama run minimax-m2-5
Hugging Face 上的权重: MiniMaxAI/MiniMax-M2.5 ↗

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
229.9B (9.8B active)
上下文窗口
1,000,000
架构
Mixture-of-Experts (256 experts, top-8, 62 layers)
提供商
MiniMax
许可证
Modified MIT (attribution required)
规格量化
Q4_K_M
系统内存
256 GB
记录更新于
2026-02-15
许可证Modified MIT允许商业使用

Commercial use permitted. No usage restrictions beyond attribution.

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。

最适合software engineeringlong contextenterprisecost efficient

我的 GPU 能运行 MiniMax M2.5 230B 吗?

MiniMax M2.5 230B — 常见问题

How much VRAM does MiniMax M2.5 230B need?

About 140 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 MiniMax M2.5 230B run on an RTX 4090 (24 GB)?

No. MiniMax M2.5 230B needs about 140 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 MiniMax M2.5 230B locally?

Install Ollama and run `ollama run minimax-m2-5`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.