← Back to community benchmarks
Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
Performance
8k
tokens
2,163
PP tok/s
62.0
TG tok/s
3788
TTFT (ms)
36.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,360 | 65.8 | 35.4 GB | view |
| 4k | 2,093 | 64.6 | 36.2 GB | view |
| 8k | 2,163 | 62.0 | 36.7 GB | current |
| 16k | 2,060 | 60.0 | 37.4 GB | view |
| 32k | 1,725 | 54.0 | 38.9 GB | view |
| 64k | 1,281 | 44.0 | 41.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 65.8 | 1.00× |
| 2× | 106.3 | 1.62× |
| 4× | 142.3 | 2.16× |
| 8× | 285.0 | 4.33× |