← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
873.4
PP tok/s
71.9
TG tok/s
9379
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 | 821.5 | 75.6 | 20.0 GB | view |
| 4k | 879.6 | 79.1 | 20.2 GB | view |
| 8k | 873.4 | 71.9 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 75.6 | 1.00× |
| 2× | 129.0 | 1.71× |
| 4× | 166.8 | 2.21× |