← Back to community benchmarks
Qwen3.5-35B-A3B-Heretic
Performance
1k
tokens
831.7
PP tok/s
82.3
TG tok/s
1231
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 831.7 | 82.3 | 20.1 GB | current |
| 4k | 896.0 | 82.1 | 20.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.3 | 1.00× |
| 2× | 132.2 | 1.61× |
| 4× | 159.8 | 1.94× |