← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
64k
tokens
1,823
PP tok/s
55.1
TG tok/s
35958
TTFT (ms)
33.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,904 | 103.1 | 27.7 GB | view |
| 4k | 2,112 | 98.0 | 28.5 GB | view |
| 8k | 2,541 | 96.5 | 28.9 GB | view |
| 16k | 2,640 | 86.8 | 29.5 GB | view |
| 32k | 2,367 | 74.7 | 30.8 GB | view |
| 64k | 1,823 | 55.1 | 33.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 103.1 | 1.00× |
| 2× | 160.8 | 1.56× |
| 4× | 206.0 | 2.00× |