← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
303.4
PP tok/s
57.1
TG tok/s
3375
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 303.4 | 57.1 | 20.1 GB | current |
| 4k | 323.1 | 52.8 | 20.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.1 | 1.00× |
| 2× | 68.9 | 1.21× |
| 4× | 76.9 | 1.35× |