← Back to community benchmarks
Qwen3.6-27B
Performance
16k
tokens
162.8
PP tok/s
16.5
TG tok/s
100630
TTFT (ms)
18.4
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.8rc1
macOS
macOS 15.7.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 183.4 | 22.5 | 15.1 GB | view |
| 4k | 193.1 | 21.3 | 16.5 GB | view |
| 16k | 162.8 | 16.5 | 18.4 GB | current |
| 64k | 124.2 | 6.5 | 25.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.5 | 1.00× |
| 2× | 27.2 | 1.21× |