← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
32k
tokens
1,791
PP tok/s
52.8
TG tok/s
18297
TTFT (ms)
23.4
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.24
macOS
macOS 26.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,992 | 74.7 | 20.1 GB | view |
| 4k | 2,328 | 71.7 | 21.1 GB | view |
| 8k | 2,315 | 68.2 | 21.4 GB | view |
| 16k | 2,127 | 62.3 | 22.0 GB | view |
| 32k | 1,791 | 52.8 | 23.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 74.7 | 1.00× |
| 2× | 120.0 | 1.61× |
| 4× | 168.6 | 2.26× |