← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
1,742
PP tok/s
101.6
TG tok/s
588
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19.dev2
macOS
macOS 26.3.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,742 | 101.6 | 20.1 GB | current |
| 4k | 1,894 | 119.7 | 21.0 GB | view |
| 8k | 1,789 | 116.0 | 21.4 GB | view |
| 16k | 1,597 | 104.3 | 22.0 GB | view |
| 32k | 1,319 | 92.1 | 23.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 101.6 | 1.00× |
| 2× | 205.0 | 2.02× |
| 4× | 306.1 | 3.01× |
| 8× | 381.2 | 3.75× |