← Back to community benchmarks
Qwen3.5-27B
Performance
1k
tokens
180.8
PP tok/s
32.1
TG tok/s
5663
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
64 GB
GPU Cores
60
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 180.8 | 32.1 | 16.7 GB | current |
| 4k | 182.8 | 30.0 | 18.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.1 | 1.00× |
| 2× | 40.4 | 1.26× |
| 4× | 44.3 | 1.38× |
| 8× | 47.9 | 1.49× |