← Back to community benchmarks
Qwen3.5-27B
Performance
16k
tokens
56.7
PP tok/s
5.7
TG tok/s
289159
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 60.6 | 6.4 | 16.6 GB | view |
| 4k | 61.3 | 6.4 | 16.9 GB | view |
| 8k | 58.7 | 6.2 | 17.3 GB | view |
| 16k | 56.7 | 5.7 | 18.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.4 | 1.00× |
| 2× | 13.3 | 2.08× |
| 4× | 16.3 | 2.55× |
| 8× | 16.5 | 2.58× |