← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
32k
tokens
416.9
PP tok/s
34.2
TG tok/s
78607
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 501.1 | 53.4 | 20.0 GB | view |
| 4k | 488.1 | 58.7 | 20.2 GB | view |
| 8k | 500.8 | 53.6 | 20.4 GB | view |
| 16k | 443.1 | 43.5 | 20.8 GB | view |
| 32k | 416.9 | 34.2 | 21.6 GB | current |
| 64k | 322.1 | 21.7 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.4 | 1.00× |
| 2× | 87.3 | 1.63× |
| 4× | 108.3 | 2.03× |
| 8× | 117.3 | 2.20× |