← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
392.9
PP tok/s
12.3
TG tok/s
2606
TTFT (ms)
22.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.24
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 392.9 | 12.3 | 22.1 GB | current |
| 4k | 422.1 | 12.3 | 23.6 GB | view |
| 8k | 430.2 | 12.2 | 24.3 GB | view |
| 16k | 416.3 | 11.7 | 25.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.3 | 1.00× |
| 2× | 22.3 | 1.81× |
| 4× | 28.1 | 2.28× |
| 8× | 28.8 | 2.34× |