← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6-mtp
Performance
16k
tokens
1,029
PP tok/s
46.5
TG tok/s
15929
TTFT (ms)
29.6
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 | 755.4 | 52.6 | 27.7 GB | view |
| 4k | 1,028 | 51.7 | 28.4 GB | view |
| 8k | 1,057 | 50.3 | 28.9 GB | view |
| 16k | 1,029 | 46.5 | 29.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.6 | 1.00× |
| 2× | 87.6 | 1.67× |
| 4× | 133.7 | 2.54× |