← Back to community benchmarks
Qwen3.5-27B
Performance
32k
tokens
85.3
PP tok/s
12.5
TG tok/s
384059
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
64 GB
GPU Cores
30
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 91.0 | 19.9 | 16.6 GB | view |
| 4k | 91.3 | 18.7 | 17.0 GB | view |
| 8k | 90.5 | 17.7 | 17.4 GB | view |
| 16k | 88.5 | 14.8 | 18.3 GB | view |
| 32k | 85.3 | 12.5 | 20.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.9 | 1.00× |
| 2× | 39.8 | 2.00× |
| 4× | 79.0 | 3.97× |