← Back to community benchmarks
Qwen3.5-27BMTP
Performance
16k
tokens
87.0
PP tok/s
16.3
TG tok/s
188312
TTFT (ms)
19.8
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev1
macOS
macOS 15.7.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 87.4 | 19.3 | 15.8 GB | view |
| 4k | 89.0 | 18.5 | 17.3 GB | view |
| 8k | 88.5 | 17.9 | 18.3 GB | view |
| 16k | 87.0 | 16.3 | 19.8 GB | current |
| 32k | 83.5 | 14.4 | 22.8 GB | view |
| 64k | 76.1 | 12.3 | 28.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.3 | 1.00× |
| 2× | 21.6 | 1.12× |
| 4× | 23.7 | 1.23× |