← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
886.7
PP tok/s
76.1
TG tok/s
9239
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.0
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 793.0 | 87.0 | 19.3 GB | view |
| 4k | 906.0 | 81.9 | 20.2 GB | view |
| 8k | 886.7 | 76.1 | 20.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 87.0 | 1.00× |
| 2× | 130.0 | 1.49× |
| 4× | 159.0 | 1.83× |