← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
3,834
PP tok/s
84.8
TG tok/s
4273
TTFT (ms)
37.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 27.0
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,209 | 88.3 | 35.4 GB | view |
| 4k | 4,259 | 89.1 | 36.2 GB | view |
| 8k | 3,735 | 74.9 | 36.7 GB | view |
| 16k | 3,834 | 84.8 | 37.5 GB | current |
| 32k | 3,281 | 81.4 | 39.3 GB | view |
| 64k | 2,399 | 70.6 | 42.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 88.3 | 1.00× |
| 2× | 160.5 | 1.82× |