← Back to community benchmarks
Qwen3.6-27B
Performance
4k
tokens
85.7
PP tok/s
16.8
TG tok/s
47806
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8rc1
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 86.9 | 18.4 | 15.8 GB | view |
| 4k | 85.7 | 16.8 | 17.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.4 | 1.00× |
| 2× | 19.5 | 1.06× |
| 4× | 15.1 | 0.82× |