← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
8k
tokens
433.0
PP tok/s
44.7
TG tok/s
18918
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 401.4 | 48.4 | 5.8 GB | view |
| 4k | 434.3 | 46.6 | 6.0 GB | view |
| 8k | 433.0 | 44.7 | 6.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.4 | 1.00× |
| 2× | 90.7 | 1.87× |
| 4× | 95.1 | 1.96× |
| 8× | 104.0 | 2.15× |