← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
1,476
PP tok/s
100.0
TG tok/s
694
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,476 | 100.0 | 20.1 GB | current |
| 4k | 1,840 | 94.0 | 20.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 100.0 | 1.00× |
| 2× | 159.5 | 1.59× |
| 4× | 210.0 | 2.10× |