← Back to community benchmarks
Qwen3.6-35B-A3B-oQ3
Performance
1k
tokens
923.8
PP tok/s
59.5
TG tok/s
1109
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 923.8 | 59.5 | 15.8 GB | current |
| 4k | 1,149 | 57.8 | 16.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.5 | 1.00× |
| 2× | 86.8 | 1.46× |
| 4× | 101.4 | 1.70× |