← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
200.7
PP tok/s
25.0
TG tok/s
20414
TTFT (ms)
8.0
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
16 GB
GPU Cores
19
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 193.5 | 25.7 | 7.8 GB | view |
| 4k | 200.7 | 25.0 | 8.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.7 | 1.00× |
| 2× | 34.8 | 1.35× |
| 4× | 36.5 | 1.42× |