LLM Inference Benchmark Explorer
Laguna-S-2.1 on Thor — NVFP4, vLLM, TP1 inference benchmark
Open this configuration in the LLM Inference Benchmark Explorer
| Model | Laguna-S-2.1 |
|---|---|
| Parameters | 118B |
| Intelligence Index | — |
| Agentic Index | — |
| Device | Thor |
| Quantization | NVFP4 |
| Max C | 0 |
| Chat Capacity | 0 |
| Agentic Capacity | 0 |
| TP | — |
| DP | — |
| PP | — |
| Engine | vLLM |
| Speculative Decoding | — |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 578 | 12.92 | FAIL |
| 2 | 674 | 11.10 | FAIL |
| 4 | 847 | 8.69 | FAIL |
| 8 | 1032 | 6.48 | FAIL |
In OpenZeka's measurement, Laguna-S-2.1 (118B parameters), served in NVFP4 format with vLLM on Thor, reached a generation speed of 12.9 tok/s per request and a time to first token (TTFT) of 578 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: Jetson Thor. max_model_len 262144
Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.
In OpenZeka's measurement, Laguna-S-2.1 (118B parameters), served in NVFP4 format with vLLM on Thor, reached a generation speed of 12.9 tok/s per request and a time to first token (TTFT) of 578 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.