← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
566.5
PP tok/s
43.5
TG tok/s
7231
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 519.6 | 48.0 | 36.2 GB | view |
| 4k | 566.5 | 43.5 | 36.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.0 | 1.00× |
| 2× | 77.3 | 1.61× |
| 4× | 105.4 | 2.20× |