← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,427
PP tok/s
100.8
TG tok/s
2870
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.2.12
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,327 | 102.5 | 20.0 GB | view |
| 4k | 1,427 | 100.8 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 102.5 | 1.00× |
| 2× | 169.8 | 1.66× |
| 4× | 230.7 | 2.25× |