LLM Inference Benchmark Explorer
GLM-5.2 on 8× DGX Spark — NVFP4, vLLM, TP8 inference benchmark
Open this configuration in the LLM Inference Benchmark Explorer
| Model | GLM-5.2 |
|---|---|
| Parameters | 753B |
| Intelligence Index | 33.7 |
| Agentic Index | 38.4 |
| Device | 8× DGX Spark |
| Quantization | NVFP4 |
| Max C | 1 |
| Chat Capacity | 4 |
| Agentic Capacity | 1 |
| TP | 8 |
| DP | — |
| PP | — |
| Engine | vLLM |
| Speculative Decoding | — |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 451 | 24.86 | PASS |
| 2 | 1305 | 17.99 | FAIL |
| 4 | 1125 | 13.98 | FAIL |
| 8 | 8745 | 7.91 | FAIL |
In OpenZeka's measurement, GLM-5.2 (753B parameters), served in NVFP4 format with vLLM on 8× DGX Spark (TP=8), reached a generation speed of 24.9 tok/s per request and a time to first token (TTFT) of 451 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is 4 users for chat use and 1 for agentic use. The realistic capacity will likely fall between these two values. In scenarios dominated by coding, tool use, long workflows and multi-agent use, capacity approaches the agentic estimate; where shorter interactions, standard conversations and lighter tasks dominate, it approaches the chat estimate.
Notes: Original, 128K context. Model: nvidia/GLM-5.2-NVFP4
Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.
In OpenZeka's measurement, GLM-5.2 (753B parameters), served in NVFP4 format with vLLM on 8× DGX Spark (TP=8), reached a generation speed of 24.9 tok/s per request and a time to first token (TTFT) of 451 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is 4 users for chat use and 1 for agentic use. The realistic capacity will likely fall between these two values. In scenarios dominated by coding, tool use, long workflows and multi-agent use, capacity approaches the agentic estimate; where shorter interactions, standard conversations and lighter tasks dominate, it approaches the chat estimate.