← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
2,039
PP tok/s
50.0
TG tok/s
2009
TTFT (ms)
37.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.24
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,784 | 53.8 | 36.2 GB | view |
| 4k | 2,039 | 50.0 | 37.1 GB | current |
| 8k | 2,171 | 49.7 | 37.5 GB | view |
| 16k | 2,018 | 45.7 | 38.2 GB | view |
| 32k | 1,687 | 39.8 | 39.5 GB | view |
| 64k | 1,215 | 33.6 | 42.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.8 | 1.00× |
| 2× | 88.4 | 1.64× |
| 4× | 126.8 | 2.36× |