← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,495
PP tok/s
83.6
TG tok/s
2741
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.2.13
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,449 | 92.3 | 20.1 GB | view |
| 4k | 1,495 | 83.6 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 92.3 | 1.00× |
| 2× | 154.3 | 1.67× |
| 4× | 226.8 | 2.46× |