Will It Run AI

MiniMax

MiniMax M2.7

前沿
huggingfaceHuggingFace
Apr 2026发布日期205K tokens上下文Apache 2.0许可证85 优秀质量

MiniMax M2.7 (230B parameters) requires approximately 145.6 GB of VRAM with UD-IQ4_XS quantization. As a Mixture of Experts model with 10B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 168 GB of VRAM.

快速开始

— 复制粘贴即可本地运行

Copy-paste commands to run MiniMax M2.7 on your machine.

Run

lms load MiniMax-M2.7 && lms server start

Quick specs

Parameters230B (10B active)
Architecturemoe (MoE)
Context205K tokens
Modalitytext
Min RAM89.7 GB
Rec. RAM140.3 GB (Q4_K_M)
LicenseApache 2.0
FamilyMiniMax
✗ Vision✓ Tool Use✗ Thinking✓ Code✓ Chat

About this model

Self-evolving agent model with 230B total / 10B active MoE architecture. SOTA on SWE-Pro (56.2%) and Terminal Bench 2 (57%). Runs locally on 128GB Mac with Dynamic 4-bit GGUF.

你的硬件

检测中...

快速推荐

最佳性价比S
Mac Studio M3 Ultra 256GB~$6,999 — 20 tok/s
最佳综合S
AMD Instinct MI325X 256GB~$20,000 — 101 tok/s

最佳硬件

MiniMax M2.7 的最佳选择

AMD Instinct MI325X 256GBS
256 GB
AMD Instinct MI350X 288GBS
288 GB
NVIDIA
NVIDIA B200 180GBS
180 GB
AMD Instinct MI300X 192GBS
192 GB
NVIDIA
NVIDIA GB200 192GBS
192 GB

运行此模型

MiniMax M2.7 on AMD Instinct MI325X 256GBMiniMax M2.7 on AMD Instinct MI350X 288GBMiniMax M2.7 on NVIDIA B200 180GB

量化选项

各量化级别的 VRAM 估算

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
89.7 GB
Low—
Q3_K_S
3
112.7 GB
Low—
NVFP4
4
128.8 GB
Medium—
Q4_K_M
4
140.3 GB
Medium—
Q5_K_M
5
165.6 GB
High—
Q6_K
6
188.6 GB
High—
Q8_0
8
246.1 GB
Very High—
F16
16
471.5 GB
Maximum—

硬件兼容性

全部硬件的适配估算

打开计算器

Computing compatibility...

内存详细分析

Reference: RTX 2060 6GB

Weights140.3 GB
KV Cache3.8 GB
Runtime0.9 GB
Headroom0.6 GB

常见问题

FAQ — MiniMax M2.7

另请参阅

量化指南评分方法打开计算器