← Back to community benchmarks
community--Qwen3.6-27B
Performance
4k
tokens
822.1
PP tok/s
9.1
TG tok/s
4983
TTFT (ms)
53.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.2.dev2
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 590.1 | 9.3 | 51.9 GB | view |
| 4k | 822.1 | 9.1 | 53.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.3 | 1.00× |
| 2× | 10.2 | 1.10× |
| 4× | 18.1 | 1.95× |