← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
16k
tokens
3,901
PP tok/s
112.1
TG tok/s
4200
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.23
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,257 | 137.1 | 19.3 GB | view |
| 4k | 3,770 | 129.0 | 20.2 GB | view |
| 8k | 4,018 | 123.5 | 20.5 GB | view |
| 16k | 3,901 | 112.1 | 21.2 GB | current |
| 32k | 3,334 | 98.9 | 22.5 GB | view |
| 64k | 2,379 | 70.5 | 25.2 GB | view |
| 128k | 1,443 | 48.5 | 30.5 GB | view |
| 195k | 884.4 | 24.8 | 36.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 137.1 | 1.00× |
| 2× | 231.7 | 1.69× |
| 4× | 322.7 | 2.35× |