← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
64k
tokens
897.3
PP tok/s
31.5
TG tok/s
73041
TTFT (ms)
42.9
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
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,083 | 91.0 | 37.1 GB | view |
| 4k | 1,451 | 95.2 | 37.9 GB | view |
| 8k | 1,450 | 87.6 | 38.2 GB | view |
| 16k | 1,361 | 77.2 | 38.9 GB | view |
| 32k | 1,165 | 50.3 | 40.2 GB | view |
| 64k | 897.3 | 31.5 | 42.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 91.0 | 1.00× |
| 2× | 165.3 | 1.82× |
| 4× | 237.2 | 2.61× |