← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
183.7
PP tok/s
17.1
TG tok/s
5575
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.10
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 183.7 | 17.1 | 5.7 GB | current |
| 4k | 187.6 | 18.0 | 5.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.1 | 1.00× |
| 2× | 32.7 | 1.91× |
| 4× | 32.4 | 1.89× |