LLM Inference Benchmark Explorer
GLM-5.2 on 8× DGX Spark — NVFP4, vLLM, TP8, speculative decoding k=5 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 | Yes |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 466 | 20.73 | PASS |
| 2 | 682 | 16.24 | FAIL |
| 4 | 875 | 13.75 | FAIL |
In OpenZeka's measurement, GLM-5.2 (753B parameters), served in NVFP4 format with vLLM and speculative decoding on 8× DGX Spark (TP=8), reached a generation speed of 20.7 tok/s per request and a time to first token (TTFT) of 466 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: V3 Final, 256K context, TP=8, EP, GMU 0.75, KV fp8_ds_mla
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 and speculative decoding on 8× DGX Spark (TP=8), reached a generation speed of 20.7 tok/s per request and a time to first token (TTFT) of 466 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.