← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
395.4
PP tok/s
27.0
TG tok/s
2590
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.8
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 395.4 | 27.0 | 9.9 GB | current |
| 4k | 422.2 | 26.1 | 10.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.0 | 1.00× |
| 2× | 52.1 | 1.93× |
| 4× | 72.7 | 2.69× |
| 8× | 145.1 | 5.37× |