← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
64k
tokens
328.2
PP tok/s
8.9
TG tok/s
199667
TTFT (ms)
29.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.14
macOS
macOS 26.3
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 395.5 | 12.9 | 22.0 GB | view |
| 4k | 439.5 | 12.7 | 22.4 GB | view |
| 8k | 436.8 | 12.4 | 22.8 GB | view |
| 16k | 421.6 | 11.7 | 23.7 GB | view |
| 32k | 390.1 | 10.6 | 25.5 GB | view |
| 64k | 328.2 | 8.9 | 29.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.9 | 1.00× |
| 2× | 22.7 | 1.76× |
| 4× | 27.9 | 2.16× |
| 8× | 28.9 | 2.24× |