← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
16k
tokens
43.3
PP tok/s
8.1
TG tok/s
378415
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 15.7.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 44.1 | 10.5 | 15.8 GB | view |
| 4k | 44.7 | 10.3 | 16.1 GB | view |
| 8k | 44.1 | 9.0 | 16.6 GB | view |
| 16k | 43.3 | 8.1 | 17.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.5 | 1.00× |
| 2× | 11.8 | 1.12× |
| 4× | 12.2 | 1.16× |
| 8× | 9.5 | 0.90× |