← Back to community benchmarks
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
659.8
PP tok/s
48.2
TG tok/s
1552
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 659.8 | 48.2 | 5.3 GB | current |
| 4k | 758.6 | 46.1 | 5.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.2 | 1.00× |
| 2× | 91.0 | 1.89× |
| 4× | 130.4 | 2.71× |