LLM Inference Benchmark Explorer
Qwen3.8-27B on RTX PRO 6000 — BF16, vLLM, TP1, speculative decoding k=3 inference benchmark
Open this configuration in the LLM Inference Benchmark Explorer
| Model | Qwen3.8-27B |
|---|---|
| Parameters | 27B |
| Intelligence Index | 33.7 |
| Agentic Index | 45.8 |
| Device | RTX PRO 6000 |
| Quantization | BF16 |
| Max C | 32 |
| Chat Capacity | 31 |
| Agentic Capacity | 10 |
| TP | — |
| DP | — |
| PP | — |
| Engine | vLLM |
| Speculative Decoding | Yes |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 104 | 65.37 | PASS |
| 2 | 158 | 62.88 | PASS |
| 4 | 179 | 57.38 | PASS |
| 8 | 212 | 50.30 | PASS |
| 16 | 264 | 43.42 | PASS |
| 32 | 385 | 31.96 | PASS |
| 64 | 2698 | 16.91 | FAIL |
| 128 | 10272 | 8.66 | FAIL |
In OpenZeka's measurement, Qwen3.8-27B (27B parameters), served in BF16 format with vLLM and speculative decoding on RTX PRO 6000, reached a generation speed of 65.4 tok/s per request and a time to first token (TTFT) of 104 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is 31 users for chat use and 10 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: Speculative MTP k=3.
Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.
In OpenZeka's measurement, Qwen3.8-27B (27B parameters), served in BF16 format with vLLM and speculative decoding on RTX PRO 6000, reached a generation speed of 65.4 tok/s per request and a time to first token (TTFT) of 104 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is 31 users for chat use and 10 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.