← Back to community benchmarks
Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliteratedoQ8-mtp
Performance
1k
tokens
1,421
PP tok/s
82.7
TG tok/s
721
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,421 | 82.7 | 35.4 GB | current |
| 4k | 2,071 | 81.1 | 36.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.7 | 1.00× |
| 2× | 137.7 | 1.67× |
| 4× | 203.9 | 2.47× |