← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
96.4
PP tok/s
16.9
TG tok/s
10621
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.11
macOS
macOS 15.7.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 96.4 | 16.9 | 5.7 GB | current |
| 4k | 102.1 | 17.0 | 5.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.9 | 1.00× |
| 2× | 24.2 | 1.43× |
| 4× | 25.7 | 1.52× |