← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
4k
tokens
1,274
PP tok/s
68.0
TG tok/s
3216
TTFT (ms)
47.9
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 866.6 | 67.7 | 47.1 GB | view |
| 4k | 1,274 | 68.0 | 47.9 GB | current |
| 8k | 1,323 | 66.7 | 48.3 GB | view |
| 16k | 2,358 | 31.9 | 49.4 GB | view |
| 32k | 2,290 | 31.0 | 50.0 GB | view |
| 64k | 1,969 | 30.1 | 52.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 67.7 | 1.00× |
| 2× | 109.3 | 1.61× |
| 4× | 156.5 | 2.31× |