Back to CalculatorDeploy Now
MiniMax M2.5
HotUpgraded MoE from MiniMax
Specifications
SourceArchitectureTEXT
Parameters250B
Familyminimax
VRAM (Q4)125.0G
MoE: 30B active.
moeminimaxtrending
Build your Local Rig
Ready to run locally? Shop top-tier GPUs on Amazon for the best performance.
Instant Cloud GPUs
Running out of VRAM? Rent a high-end H100 or RTX 4090 on RunPod and deploy in seconds.
Quantization Estimates
| Format | VRAM Need | Tier |
|---|---|---|
| FP16 | 500.0 GB | Full Precision |
| Q8_0 | 250.0 GB | High |
| Q6_K | 212.5 GB | Excellent |
| Q5_K_M | 175.0 GB | Great |
| Q4_K_M | 125.0 GB | Sweet Spot |
| Q2_K | 75.0 GB | Emergency |
Share this Model
Send these specs directly to your community.
Similar Models
MiniMax M2
200BCapable chat model with strong performance
MiniMax M1
456BLightning reasoning model, hybrid thinking
MiniMax M2.7
230BMiniMax M2.7 is a 230B sparse MoE model built for complex agentic workflows. 10B parameters active per token. Open weights under non-commercial license. Released March 2026.