← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
1,687
PP tok/s
93.3
TG tok/s
4856
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,689 | 111.2 | 20.1 GB | view |
| 4k | 1,746 | 99.3 | 20.2 GB | view |
| 8k | 1,687 | 93.3 | 20.4 GB | current |
| 16k | 1,559 | 65.4 | 20.8 GB | view |
| 32k | 1,295 | 48.5 | 21.6 GB | view |
| 64k | 1,031 | 28.1 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 111.2 | 1.00× |
| 2× | 186.6 | 1.68× |
| 4× | 270.9 | 2.44× |
| 8× | 350.9 | 3.16× |