MiniMax
MiniMax M2.7
最先端
Apr 2026公開日205K トークンコンテキストApache 2.0ライセンス85 優秀品質
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.
はじめに
— コピー&ペーストでローカル実行Copy-paste commands to run MiniMax M2.7 on your machine.
Run
lms load MiniMax-M2.7 && lms server startQuick 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
おすすめ
最適なハードウェア
MiniMax M2.7のおすすめ
このモデルを実行
量子化オプション
量子化レベル別VRAM推定値
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
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 | — |
ハードウェア互換性
全ハードウェアの適合度推定
Computing compatibility...
メモリ内訳
Reference: RTX 2060 6GB
Weights140.3 GB
KV Cache3.8 GB
Runtime0.9 GB
Headroom0.6 GB
よくある質問
FAQ — MiniMax M2.7
関連項目