← Back to community benchmarks
Qwen3.6-35B-A3BoQ4
Performance
1k
tokens
1,215
PP tok/s
121.3
TG tok/s
843
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 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 | 1,215 | 121.3 | 20.1 GB | current |
| 4k | 3,059 | 114.9 | 20.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 121.3 | 1.00× |
| 2× | 188.0 | 1.55× |
| 4× | 272.9 | 2.25× |
| 8× | 347.6 | 2.87× |