← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
1,588
PP tok/s
75.9
TG tok/s
10319
TTFT (ms)
37.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,325 | 84.0 | 35.4 GB | view |
| 4k | 1,656 | 82.4 | 36.2 GB | view |
| 8k | 1,700 | 82.3 | 36.5 GB | view |
| 16k | 1,588 | 75.9 | 37.4 GB | current |
| 32k | 1,377 | 70.7 | 38.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 84.0 | 1.00× |
| 2× | 148.0 | 1.76× |
| 4× | 213.7 | 2.54× |
| 8× | 251.1 | 2.99× |