← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
1k
tokens
1,746
PP tok/s
98.7
TG tok/s
587
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,746 | 98.7 | 35.4 GB | current |
| 4k | 3,429 | 96.6 | 36.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 98.7 | 1.00× |
| 2× | 159.1 | 1.61× |
| 4× | 239.7 | 2.43× |