← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
552.3
PP tok/s
50.2
TG tok/s
1854
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 50.2 | 1.00× |
| 2× | 79.0 | 1.57× |
| 4× | 109.6 | 2.18× |
| 8× | 130.9 | 2.61× |