← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
106.4
PP tok/s
9.7
TG tok/s
9622
TTFT (ms)
9.7
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 106.4 | 9.7 | 9.7 GB | current |
| 4k | 108.7 | 9.9 | 10.0 GB | view |
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× |