← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
191.1
PP tok/s
8.7
TG tok/s
5358
TTFT (ms)
9.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.11
macOS
macOS 26.0
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 191.1 | 8.7 | 9.7 GB | current |
| 4k | 194.3 | 10.1 | 10.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.7 | 1.00× |
| 2× | 20.1 | 2.31× |
| 4× | 31.6 | 3.63× |