← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
392.1
PP tok/s
49.9
TG tok/s
20891
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 427.0 | 56.3 | 20.0 GB | view |
| 4k | 439.6 | 53.6 | 20.2 GB | view |
| 8k | 392.1 | 49.9 | 20.4 GB | current |
| 16k | 358.0 | 39.4 | 20.8 GB | view |
| 32k | 300.3 | 29.8 | 21.6 GB | view |
| 64k | 250.9 | 9.4 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.3 | 1.00× |
| 2× | 78.8 | 1.40× |
| 4× | 92.1 | 1.64× |
| 8× | 103.3 | 1.83× |