← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
195k
tokens
595.3
PP tok/s
35.0
TG tok/s
335971
TTFT (ms)
54.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.4.1
macOS
macOS 26.5
Context
200,000
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,409 | 80.9 | 35.4 GB | view |
| 4k | 1,968 | 76.4 | 36.2 GB | view |
| 16k | 1,929 | 72.0 | 37.1 GB | view |
| 128k | 831.4 | 44.9 | 46.5 GB | view |
| 195k | 595.3 | 35.0 | 54.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 80.9 | 1.00× |
| 2× | 132.3 | 1.64× |
| 4× | 202.7 | 2.51× |