← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2
Performance
1k
tokens
696.5
PP tok/s
25.9
TG tok/s
1470
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.5
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 696.5 | 25.9 | 5.7 GB | current |
| 4k | 782.8 | 24.4 | 6.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.9 | 1.00× |
| 2× | 51.9 | 2.00× |
| 4× | 72.4 | 2.80× |
| 8× | 72.2 | 2.79× |