← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
1,701
PP tok/s
80.3
TG tok/s
4817
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,348 | 86.5 | 35.4 GB | view |
| 4k | 1,706 | 83.4 | 36.2 GB | view |
| 8k | 1,701 | 80.3 | 36.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 86.5 | 1.00× |
| 2× | 139.0 | 1.61× |