← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
253.6
PP tok/s
35.7
TG tok/s
4038
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 15.7
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 253.6 | 35.7 | 16.7 GB | current |
| 4k | 166.4 | 23.2 | 18.2 GB | view |