← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,989
PP tok/s
94.7
TG tok/s
2059
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.15
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,495 | 100.1 | 20.1 GB | view |
| 4k | 1,989 | 94.7 | 21.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 100.1 | 1.00× |
| 2× | 164.6 | 1.64× |
| 4× | 205.6 | 2.05× |