← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
8k
tokens
315.6
PP tok/s
16.6
TG tok/s
25959
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 286.8 | 17.2 | 15.8 GB | view |
| 4k | 295.8 | 16.8 | 17.3 GB | view |
| 8k | 315.6 | 16.6 | 18.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.2 | 1.00× |
| 2× | 27.6 | 1.60× |
| 4× | 31.5 | 1.83× |
| 8× | 31.2 | 1.81× |