LLM Inference Benchmark Explorer

Qwen3-VL-30B-A3B-Instruct on Thor — FP8, vLLM, TP1, speculative decoding inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelQwen3-VL-30B-A3B-Instruct
Parameters30B
Intelligence Index9.5
Agentic Index—
DeviceThor
QuantizationFP8
Max C8
Chat Capacity32
Agentic Capacity12
TP—
DP—
PP—
EnginevLLM
Speculative DecodingYes
CTTFT (ms)TPS (tok/s)Status
17557.44PASS
210942.23PASS
414928.16PASS
818921.32PASS
1622515.95FAIL
3230012.61FAIL

In OpenZeka's measurement, Qwen3-VL-30B-A3B-Instruct (30B parameters), served in FP8 format with vLLM and speculative decoding on Thor, reached a generation speed of 57.4 tok/s per request and a time to first token (TTFT) of 75 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 32 users for chat use and 12 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 decoding used; mechanism and depth not recorded. Model: Qwen/Qwen3-VL-30B-A3B-Instruct-FP8. 256K context

Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.