← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
162.4
PP tok/s
18.5
TG tok/s
25219
TTFT (ms)
5.9
Peak mem (GB)
Hardware
Chip
M4 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.8
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 160.6 | 19.2 | 5.7 GB | view |
| 4k | 162.4 | 18.5 | 5.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.2 | 1.00× |
| 2× | 36.5 | 1.90× |
| 4× | 28.1 | 1.46× |