← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,677
PP tok/s
82.7
TG tok/s
2442
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.9
macOS
macOS 26.3.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,687 | 84.9 | 36.2 GB | view |
| 4k | 1,677 | 82.7 | 36.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 84.9 | 1.00× |
| 2× | 140.1 | 1.65× |
| 4× | 204.7 | 2.41× |