← Leaderboard
aeon-7/qwen3.6-27b-aeon-ultimate-uncensored

qwen3.6-27b-aeon-ultimate-uncensored

vLLM 27B General
Throughput @ 4k
26.0t/s
@ 50k fill
14.5t/s
@ 100k fill
11.4t/s
Retention 100k÷4k
44%
Engine
vLLM
Parameters
27B
Released
2026-04-24

Headline numbers are perfbench-metrics (PBM): decode tok/s after a fixed context fill (4k / 50k / 100k), same agent-style workload as bench v2. Retention is how much of the 4k speed remains at 100k.

Fill curve

Throughput vs context fill — how the model holds up as the window grows.

29 15 0 26.0 4k 14.5 50k 11.4 100k tok/s

Golden profile

aeon-qwen3-6-27b-dflash-n10

Bench notes

PBM 4k @ 26.0 tok/s — perfbench-metrics — profile=aeon-qwen3-6-27b-dflash-n10

Benchmarked 2026-07-10
SparkBench · GB10 · single node