← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
122.1
PP tok/s
14.9
TG tok/s
8385
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.9
macOS
macOS 15.6.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 122.1 | 14.9 | 15.8 GB | current |
| 4k | 108.7 | 14.5 | 16.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.9 | 1.00× |
| 2× | 26.8 | 1.80× |
| 4× | 31.2 | 2.09× |