← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
876.2
PP tok/s
74.9
TG tok/s
9349
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 867.2 | 82.8 | 20.1 GB | view |
| 4k | 899.9 | 79.2 | 20.2 GB | view |
| 8k | 876.2 | 74.9 | 20.4 GB | current |
| 16k | 805.6 | 57.7 | 20.8 GB | view |
| 32k | 693.2 | 40.6 | 21.6 GB | view |
| 64k | 537.6 | 25.9 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.8 | 1.00× |
| 2× | 131.3 | 1.59× |
| 4× | 167.3 | 2.02× |