← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
222.4
PP tok/s
20.7
TG tok/s
18417
TTFT (ms)
5.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 215.0 | 21.4 | 5.7 GB | view |
| 4k | 222.4 | 20.7 | 5.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.4 | 1.00× |
| 2× | 42.2 | 1.97× |
| 4× | 53.7 | 2.51× |