← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
417.6
PP tok/s
44.8
TG tok/s
2452
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 417.6 | 44.8 | 19.2 GB | current |
| 4k | 460.7 | 43.3 | 19.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.8 | 1.00× |
| 2× | 69.7 | 1.56× |
| 4× | 82.1 | 1.83× |