← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
1,118
PP tok/s
75.1
TG tok/s
3663
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
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 | 942.2 | 82.1 | 19.2 GB | view |
| 4k | 1,118 | 75.1 | 20.0 GB | current |
| 64k | 647.2 | 31.9 | 25.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.1 | 1.00× |
| 2× | 135.5 | 1.65× |
| 4× | 187.0 | 2.28× |