← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
8k
tokens
117.6
PP tok/s
14.4
TG tok/s
69633
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 123.3 | 15.4 | 15.8 GB | view |
| 4k | 124.9 | 14.8 | 16.1 GB | view |
| 8k | 117.6 | 14.4 | 16.6 GB | current |
| 16k | 117.5 | 13.1 | 17.5 GB | view |
| 32k | 111.9 | 10.6 | 19.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.4 | 1.00× |
| 2× | 29.6 | 1.92× |
| 4× | 33.1 | 2.15× |
| 8× | 34.3 | 2.23× |