← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
16k
tokens
2,144
PP tok/s
79.3
TG tok/s
7643
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,341 | 101.8 | 19.3 GB | view |
| 4k | 2,150 | 98.9 | 20.0 GB | view |
| 8k | 2,241 | 85.9 | 20.4 GB | view |
| 16k | 2,144 | 79.3 | 21.0 GB | current |
| 32k | 1,816 | 59.2 | 22.3 GB | view |
| 64k | 1,332 | 41.0 | 25.0 GB | view |
| 128k | 833.0 | 26.3 | 30.4 GB | view |
| 195k | 602.6 | 19.3 | 36.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 101.8 | 1.00× |
| 2× | 150.8 | 1.48× |
| 4× | 196.9 | 1.93× |
| 8× | 240.3 | 2.36× |