← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
32k
tokens
669.2
PP tok/s
39.5
TG tok/s
48967
TTFT (ms)
29.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 850.8 | 61.7 | 28.1 GB | view |
| 4k | 864.0 | 55.4 | 28.3 GB | view |
| 8k | 839.2 | 55.7 | 28.5 GB | view |
| 16k | 775.0 | 49.4 | 28.9 GB | view |
| 32k | 669.2 | 39.5 | 29.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.7 | 1.00× |
| 2× | 95.7 | 1.55× |
| 4× | 112.7 | 1.83× |
| 8× | 131.5 | 2.13× |