← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
820.7
PP tok/s
27.3
TG tok/s
19963
TTFT (ms)
37.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.2rc1
macOS
macOS 26.5.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 694.4 | 29.5 | 35.4 GB | view |
| 4k | 886.0 | 21.7 | 36.2 GB | view |
| 16k | 820.7 | 27.3 | 37.1 GB | current |
| 64k | 490.1 | 15.4 | 41.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.5 | 1.00× |
| 2× | 31.6 | 1.07× |
| 4× | 39.3 | 1.33× |
| 8× | 92.1 | 3.12× |