← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-qx64-hi
Performance
4k
tokens
121.5
PP tok/s
11.4
TG tok/s
33703
TTFT (ms)
20.3
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 120.1 | 12.4 | 19.9 GB | view |
| 4k | 121.5 | 11.4 | 20.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.4 | 1.00× |
| 2× | 22.2 | 1.79× |
| 4× | 25.1 | 2.02× |