← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
594.6
PP tok/s
74.1
TG tok/s
6889
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
64 GB
GPU Cores
30
Software
oMLX
v0.2.6
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 545.7 | 75.9 | 20.1 GB | view |
| 4k | 594.6 | 74.1 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 75.9 | 1.00× |
| 2× | 106.7 | 1.41× |
| 4× | 127.7 | 1.68× |