← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
210.5
PP tok/s
15.7
TG tok/s
4865
TTFT (ms)
7.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 210.5 | 15.7 | 7.8 GB | current |
| 4k | 217.8 | 15.5 | 8.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.7 | 1.00× |
| 2× | 29.7 | 1.89× |
| 4× | 30.7 | 1.96× |