← Back to community benchmarks
qwen3.5
Performance
1k
tokens
30.5
PP tok/s
7.0
TG tok/s
33591
TTFT (ms)
12.6
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 30.5 | 7.0 | 12.6 GB | current |
| 4k | 30.7 | 6.7 | 13.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.0 | 1.00× |
| 2× | 7.4 | 1.06× |
| 4× | 7.4 | 1.06× |