← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
16k
tokens
811.0
PP tok/s
66.2
TG tok/s
20202
TTFT (ms)
20.8
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 848.9 | 88.5 | 20.0 GB | view |
| 4k | 907.0 | 82.9 | 20.2 GB | view |
| 8k | 880.4 | 77.4 | 20.4 GB | view |
| 16k | 811.0 | 66.2 | 20.8 GB | current |
| 32k | 693.1 | 49.1 | 21.6 GB | view |
| 64k | 535.7 | 34.4 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 88.5 | 1.00× |
| 2× | 132.5 | 1.50× |
| 4× | 165.3 | 1.87× |