← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6-mtp
Performance
16k
tokens
1,033
PP tok/s
53.5
TG tok/s
15868
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
128 GB
GPU Cores
64
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 745.8 | 60.4 | 28.3 GB | view |
| 4k | 1,025 | 58.1 | 29.1 GB | view |
| 8k | 1,053 | 55.6 | 29.6 GB | view |
| 16k | 1,033 | 53.5 | 30.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 60.4 | 1.00× |
| 2× | 87.5 | 1.45× |
| 4× | 108.5 | 1.80× |