← Back to community benchmarks
Qwen3.6-27B-AEON-Ultimate-Uncensored-oQ8-mtp
Performance
1k
tokens
233.2
PP tok/s
26.5
TG tok/s
4392
TTFT (ms)
28.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 233.2 | 26.5 | 28.8 GB | current |
| 4k | 243.7 | 26.4 | 30.3 GB | view |