← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
1,144
PP tok/s
56.9
TG tok/s
3580
TTFT (ms)
20.3
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 899.3 | 59.5 | 19.6 GB | view |
| 4k | 1,144 | 56.9 | 20.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.5 | 1.00× |
| 2× | 89.9 | 1.51× |
| 4× | 108.7 | 1.83× |