← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
2,289
PP tok/s
88.4
TG tok/s
3578
TTFT (ms)
21.4
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.20.dev3
macOS
macOS 26.3.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,996 | 96.6 | 20.1 GB | view |
| 4k | 2,344 | 90.4 | 21.0 GB | view |
| 8k | 2,289 | 88.4 | 21.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.6 | 1.00× |
| 2× | 153.6 | 1.59× |
| 4× | 207.5 | 2.15× |
| 8× | 262.7 | 2.72× |