← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
212.3
PP tok/s
12.2
TG tok/s
4824
TTFT (ms)
9.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.2 | 1.00× |
| 2× | 24.5 | 2.01× |
| 4× | 38.8 | 3.18× |
| 8× | 39.3 | 3.22× |