LLM Inference Benchmark Explorer
MiniMax-M2.7 on 2× DGX Spark — NVFP4, vLLM, TP1, PP2 inference benchmark
Open this configuration in the LLM Inference Benchmark Explorer
| Model | MiniMax-M2.7 |
|---|---|
| Parameters | 229B |
| Intelligence Index | 22.8 |
| Agentic Index | 15.3 |
| Device | 2× DGX Spark |
| Quantization | NVFP4 |
| Max C | 0 |
| Chat Capacity | 0 |
| Agentic Capacity | 0 |
| TP | — |
| DP | — |
| PP | 2 |
| Engine | vLLM |
| Speculative Decoding | — |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 396 | 17.20 | FAIL |
| 2 | 371 | 14.65 | FAIL |
| 4 | 501 | 10.73 | FAIL |
| 8 | 670 | 7.52 | FAIL |
In OpenZeka's measurement, MiniMax-M2.7 (229B parameters), served in NVFP4 format with vLLM on 2× DGX Spark (PP=2), reached a generation speed of 17.2 tok/s per request and a time to first token (TTFT) of 396 ms with a single request.
At the default speed targets (at least 20 tok/s per request, TTFT at most 1,000 ms) there is no capacity estimate for this configuration: no measured load level met them.
Notes: PP=2 (pipeline parallel)
Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.
In OpenZeka's measurement, MiniMax-M2.7 (229B parameters), served in NVFP4 format with vLLM on 2× DGX Spark (PP=2), reached a generation speed of 17.2 tok/s per request and a time to first token (TTFT) of 396 ms with a single request.
At the default speed targets (at least 20 tok/s per request, TTFT at most 1,000 ms) there is no capacity estimate for this configuration: no measured load level met them.