LLM Inference Benchmark Explorer
GLM-5.2 on 4× DGX Spark — INT4, vLLM, TP4, speculative decoding k=4 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 | 4× DGX Spark |
| Quantization | INT4 |
| Max C | 2 |
| Chat Capacity | 8 |
| Agentic Capacity | 3 |
| TP | 4 |
| DP | — |
| PP | — |
| Engine | vLLM |
| Speculative Decoding | Yes |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 490 | 27.39 | PASS |
| 2 | 717 | 20.02 | PASS |
| 4 | 955 | 14.33 | FAIL |
| 8 | 6560 | 8.51 | FAIL |
In OpenZeka's measurement, GLM-5.2 (753B parameters), served in INT4 format with vLLM and speculative decoding on 4× DGX Spark (TP=4), reached a generation speed of 27.4 tok/s per request and a time to first token (TTFT) of 490 ms with a single request.
Considering the speed targets alone (the KV cache limit was not calculated for this configuration), the estimated capacity is 8 users for chat use and 3 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: TP=4, DCP=4, cudagraph FULL, GMU 0.885, B12X_MLA_SPARSE
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 INT4 format with vLLM and speculative decoding on 4× DGX Spark (TP=4), reached a generation speed of 27.4 tok/s per request and a time to first token (TTFT) of 490 ms with a single request.
Considering the speed targets alone (the KV cache limit was not calculated for this configuration), the estimated capacity is 8 users for chat use and 3 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.