← Back to community benchmarks
Qwen3.5-27B
Performance
1k
tokens
240.5
PP tok/s
20.5
TG tok/s
4259
TTFT (ms)
22.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 240.5 | 20.5 | 22.9 GB | current |
| 4k | 235.0 | 19.5 | 23.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.5 | 1.00× |
| 2× | 31.0 | 1.51× |
| 4× | 28.6 | 1.40× |