← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
747.5
PP tok/s
59.5
TG tok/s
10959
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 643.1 | 64.0 | 19.2 GB | view |
| 4k | 736.1 | 62.8 | 20.0 GB | view |
| 8k | 747.5 | 59.5 | 20.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.0 | 1.00× |
| 2× | 94.6 | 1.48× |
| 4× | 126.5 | 1.98× |