MiniMax M2.7 needs ~163.0 GB VRAM. NVIDIA B200 180GB has 180.0 GB. With UD-IQ4_XS quantization, expect ~143 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
314.2 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
10.4 tok/s
TTFT
18536 ms
Safe context
4K
Memory
494.2 GB / 180.0 GB
Offload
60%
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Tight fit | 143.1 tok/s | 738 ms | 88K |
| Coding | S | Tight fit | 143.1 tok/s | 1353 ms | 88K |
| Agentic Coding | S | Tight fit | 143.1 tok/s | 1968 ms | 88K |
| Reasoning | S | Tight fit | 143.1 tok/s | 1599 ms | 88K |
| RAG | S | Tight fit | 143.1 tok/s | 2460 ms | 88K |
How MiniMax M2.7 (230B params) fits at each quantization level on NVIDIA B200 180GB (180.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 89.7 GB | Low | A84 |
Q3_K_S | 3 | 112.7 GB | Low | A84 |
NVFP4 | 4 |
Copy-paste commands to run MiniMax M2.7 on your machine.
Run
lms load MiniMax-M2.7 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 284B | S | 144.8 tok/s | ||
| 235B | S | 136.8 tok/s |
Yes, NVIDIA B200 180GB can run MiniMax M2.7 with a S grade (Tight fit). Expected decode speed: 143.1 tok/s.
MiniMax M2.7 (230B parameters) requires approximately 163.0 GB of memory with UD-IQ4_XS quantization.
The recommended quantization for MiniMax M2.7 is UD-IQ4_XS, which balances quality and memory efficiency.
On NVIDIA B200 180GB, MiniMax M2.7 achieves approximately 143.1 tokens per second decode speed with a time-to-first-token of 1353ms using UD-IQ4_XS quantization.
For coding workloads, MiniMax M2.7 on NVIDIA B200 180GB receives a S grade with 143.1 tok/s and 88K context.
On NVIDIA B200 180GB, MiniMax M2.7 can safely use up to 88K tokens of context. The model's official context limit is 205K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/minimax-m2-7-on-b200-180gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
128.8 GB |
| Medium |
| A84 |
Q4_K_MBest for your GPU | 4 | 140.3 GB | Medium | A84 |
Q5_K_M | 5 | 165.6 GB | High | F0 |
Q6_K | 6 | 188.6 GB | High | F0 |
Q8_0 | 8 | 246.1 GB | Very High | F0 |
F16 | 16 | 471.5 GB | Maximum | F0 |