← Back to community benchmarks
Qwen3.6-35B-A3B-oQ8
Performance
64k
tokens
1,782
PP tok/s
52.6
TG tok/s
36779
TTFT (ms)
41.2
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 | 1,987 | 95.9 | 35.4 GB | view |
| 4k | 2,076 | 92.3 | 36.2 GB | view |
| 8k | 2,484 | 90.5 | 36.5 GB | view |
| 16k | 2,553 | 83.5 | 37.1 GB | view |
| 32k | 2,314 | 71.1 | 38.5 GB | view |
| 64k | 1,782 | 52.6 | 41.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 95.9 | 1.00× |
| 2× | 149.4 | 1.56× |
| 4× | 206.8 | 2.16× |