← Back to community benchmarks
Qwen3.6-35B-A3B-OptiQ
Performance
1k
tokens
1,375
PP tok/s
100.6
TG tok/s
745
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,375 | 100.6 | 20.7 GB | current |
| 4k | 1,719 | 97.4 | 21.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 100.6 | 1.00× |
| 2× | 161.4 | 1.60× |
| 4× | 234.5 | 2.33× |