← Back to community benchmarks
Qwen3.5-27B
Performance
1k
tokens
224.3
PP tok/s
33.5
TG tok/s
4566
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 224.3 | 33.5 | 16.6 GB | current |
| 4k | 228.4 | 31.0 | 17.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.5 | 1.00× |
| 2× | 47.2 | 1.41× |
| 4× | 54.8 | 1.64× |