← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4
Performance
16k
tokens
1,574
PP tok/s
96.0
TG tok/s
10407
TTFT (ms)
21.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,278 | 114.0 | 19.9 GB | view |
| 4k | 1,735 | 110.3 | 20.7 GB | view |
| 8k | 1,727 | 105.6 | 21.1 GB | view |
| 16k | 1,574 | 96.0 | 21.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 114.0 | 1.00× |
| 2× | 181.1 | 1.59× |
| 4× | 243.8 | 2.14× |
| 8× | 303.3 | 2.66× |