← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
913.3
PP tok/s
80.8
TG tok/s
4485
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 899.3 | 85.1 | 20.1 GB | view |
| 4k | 913.3 | 80.8 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.1 | 1.00× |
| 2× | 135.0 | 1.59× |
| 4× | 168.5 | 1.98× |