← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
108.7
PP tok/s
9.9
TG tok/s
37677
TTFT (ms)
10.0
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 106.4 | 9.7 | 9.7 GB | view |
| 4k | 108.7 | 9.9 | 10.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.7 | 1.00× |
| 2× | 19.7 | 2.03× |
| 4× | 28.5 | 2.94× |
| 8× | 21.0 | 2.16× |