← Leaderboard

Qwen3-30B-A3B

NVFP4 MoE · 3B active / 30B total vLLM AgentsGeneralReasoning

Throughput

  • @ 4k 74.2t/s

Decode tok/s after a fixed context fill (PBM) — same agent-style workload as bench v2.

Recipe

Profile
nvidia-qwen3-30b-a3b-eugr
Engine
vLLM
Context
40k · fp8 KV
Served as
qwen3-30b-a3b

Run on your Spark

single node shell
spark inference up nvidia-qwen3-30b-a3b-eugr

Why we run it

Faster MoE sibling for interactive agent loops — lower latency and memory pressure when max intelligence isn't required.

Bench notes

PBM 4k @ 74.2 tok/s — perfbench-metrics — profile=nvidia-qwen3-30b-a3b-eugr

Measurement history

Context ladder

Older bench-v2 / golden cells at each benched context window (single measurement).

Context KV Throughput
@ 40k peak golden 72.3t/s

Benchmark runs

Recorded inference benchmark sessions for this model's profile.

Date Profile Method Avg Session t/s Range Fill Tool
2026-06-28latest nvidia-qwen3-30b-a3b-eugr bench-agent-v2v2.0 72.3t/s ~18,432 fail
golden 40k/fp8 @ 72.3 tok/s — fill~18432 — bench-agent-v2 — tool_ok=False
2026-06-21 nvidia-qwen3-30b-a3b-eugr bench-agent 74.6t/s 74.2 · 74.7 · 75.0 74.2–75.0 @ 40k
agent bench avg 74.6 tok/s over 3 sessions × 3 turns (2304 tok in 30.9s)
Benchmarked 2026-07-10
SparkBench · GB10 · single node