← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
451.8
PP tok/s
43.0
TG tok/s
9066
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 426.0 | 47.3 | 19.2 GB | view |
| 4k | 451.8 | 43.0 | 19.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.3 | 1.00× |
| 2× | 71.2 | 1.51× |
| 4× | 80.7 | 1.71× |