← Back to community benchmarks
Qwen3.5-27B
Performance
4k
tokens
277.2
PP tok/s
9.0
TG tok/s
14777
TTFT (ms)
54.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 267.3 | 9.1 | 52.5 GB | view |
| 4k | 277.2 | 9.0 | 54.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.1 | 1.00× |
| 2× | 7.9 | 0.87× |
| 4× | 15.5 | 1.70× |
| 8× | 30.3 | 3.33× |