← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
1k
tokens
1,960
PP tok/s
98.1
TG tok/s
523
TTFT (ms)
27.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,960 | 98.1 | 27.7 GB | current |
| 4k | 2,239 | 97.5 | 28.5 GB | view |
| 8k | 2,696 | 98.0 | 28.9 GB | view |
| 16k | 2,772 | 87.4 | 29.5 GB | view |
| 32k | 2,413 | 75.1 | 30.8 GB | view |
| 64k | 1,868 | 57.7 | 33.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 98.1 | 1.00× |
| 2× | 155.8 | 1.59× |
| 4× | 217.6 | 2.22× |