← Back to community benchmarks
Qwen3.5-27B
Performance
8k
tokens
320.0
PP tok/s
33.6
TG tok/s
25597
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 319.4 | 35.7 | 16.6 GB | view |
| 4k | 324.1 | 35.7 | 17.0 GB | view |
| 8k | 320.0 | 33.6 | 17.4 GB | current |
| 16k | 310.0 | 29.8 | 18.3 GB | view |
| 32k | 291.5 | 24.1 | 20.1 GB | view |
| 64k | 258.8 | 19.1 | 23.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.7 | 1.00× |
| 2× | 61.2 | 1.71× |
| 4× | 70.6 | 1.98× |
| 8× | 77.0 | 2.16× |