LLM Inference Benchmark Explorer

GPT-OSS 120B on 2× DGX Spark — MXFP4, vLLM, TP2 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelGPT-OSS 120B
Parameters120B
Intelligence Index11.6
Agentic Index3.7
Device2× DGX Spark
QuantizationMXFP4
Max C8
Chat Capacity32
Agentic Capacity12
TP2
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
116869.86PASS
222851.52PASS
425537.14PASS
829226.92PASS
1632019.08FAIL
3246512.63FAIL

In OpenZeka's measurement, GPT-OSS 120B (120B parameters), served in MXFP4 format with vLLM on 2× DGX Spark (TP=2), reached a generation speed of 69.9 tok/s per request and a time to first token (TTFT) of 168 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: CUTLASS MoE, FlashInfer attn. +26% TPS over TP=1 at C1

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