← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2
Performance
1k
tokens
100.8
PP tok/s
16.7
TG tok/s
10159
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 100.8 | 16.7 | 5.7 GB | current |
| 4k | 103.3 | 16.4 | 6.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.7 | 1.00× |
| 2× | 25.3 | 1.51× |
| 4× | 24.2 | 1.45× |