← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
64k
tokens
1,881
PP tok/s
49.5
TG tok/s
34841
TTFT (ms)
75.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,776 | 84.6 | 69.7 GB | view |
| 4k | 3,427 | 89.5 | 70.5 GB | view |
| 8k | 2,964 | 87.1 | 70.8 GB | view |
| 16k | 3,102 | 81.8 | 71.4 GB | view |
| 32k | 2,576 | 71.6 | 72.8 GB | view |
| 64k | 1,881 | 49.5 | 75.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 84.6 | 1.00× |
| 2× | 155.1 | 1.83× |
| 4× | 217.8 | 2.57× |