← Back to community benchmarks
Qwen3.5-27B
Performance
4k
tokens
90.4
PP tok/s
18.0
TG tok/s
45333
TTFT (ms)
17.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 90.0 | 19.1 | 16.6 GB | view |
| 4k | 90.4 | 18.0 | 17.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.1 | 1.00× |
| 2× | 22.0 | 1.15× |
| 4× | 23.5 | 1.23× |