← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
85.8
PP tok/s
8.9
TG tok/s
11929
TTFT (ms)
9.7
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 85.8 | 8.9 | 9.7 GB | current |
| 4k | 58.2 | 7.1 | 10.0 GB | view |
| 8k | 58.3 | 7.3 | 10.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.9 | 1.00× |
| 2× | 10.5 | 1.18× |
| 4× | 12.9 | 1.45× |
| 8× | 9.2 | 1.03× |