← Back to community benchmarks
Qwen3.6-35B-A3B-TurboQuant
Performance
8k
tokens
3,925
PP tok/s
104.5
TG tok/s
2087
TTFT (ms)
28.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,796 | 108.7 | 27.3 GB | view |
| 4k | 3,468 | 105.1 | 28.1 GB | view |
| 8k | 3,925 | 104.5 | 28.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 108.7 | 1.00× |
| 2× | 175.4 | 1.61× |
| 4× | 251.3 | 2.31× |
| 8× | 313.8 | 2.89× |