← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
195k
tokens
257.6
PP tok/s
26.5
TG tok/s
776357
TTFT (ms)
28.4
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.5.3
macOS
macOS 27.0
Context
200,000
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 921.4 | 84.3 | 19.4 GB | view |
| 4k | 976.2 | 81.0 | 20.1 GB | view |
| 8k | 933.0 | 76.9 | 20.3 GB | view |
| 16k | 839.6 | 71.0 | 20.6 GB | view |
| 32k | 699.1 | 61.9 | 21.3 GB | view |
| 64k | 524.0 | 48.4 | 22.5 GB | view |
| 128k | 348.9 | 35.0 | 25.1 GB | view |
| 195k | 257.6 | 26.5 | 28.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 84.3 | 1.00× |
| 2× | 134.7 | 1.60× |
| 4× | 174.0 | 2.06× |
| 8× | 215.7 | 2.56× |