← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
1,887
PP tok/s
59.3
TG tok/s
4341
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.12
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,487 | 62.7 | 36.2 GB | view |
| 4k | 1,818 | 61.0 | 36.3 GB | view |
| 8k | 1,887 | 59.3 | 36.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.7 | 1.00× |
| 2× | 102.9 | 1.64× |
| 4× | 138.6 | 2.21× |
| 8× | 199.8 | 3.19× |