← Back to community benchmarks
Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
Performance
1k
tokens
1,370
PP tok/s
66.4
TG tok/s
748
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,370 | 66.4 | 35.4 GB | current |
| 4k | 2,031 | 64.3 | 36.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 66.4 | 1.00× |
| 2× | 102.1 | 1.54× |
| 4× | 139.8 | 2.11× |