← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
16k
tokens
474.1
PP tok/s
32.7
TG tok/s
34559
TTFT (ms)
37.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 480.3 | 43.8 | 36.2 GB | view |
| 4k | 537.3 | 42.1 | 36.3 GB | view |
| 8k | 531.9 | 37.5 | 36.5 GB | view |
| 16k | 474.1 | 32.7 | 37.0 GB | current |
| 32k | 459.1 | 28.8 | 37.8 GB | view |
| 64k | 396.7 | 19.3 | 39.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 43.8 | 1.00× |
| 2× | 78.0 | 1.78× |
| 4× | 89.2 | 2.04× |