← Back to community benchmarks
Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated
Performance
4k
tokens
92.6
PP tok/s
19.1
TG tok/s
44213
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 91.0 | 20.3 | 15.8 GB | view |
| 4k | 92.6 | 19.1 | 17.3 GB | current |
| 8k | 92.0 | 17.9 | 17.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.3 | 1.00× |
| 2× | 23.2 | 1.14× |
| 4× | 24.5 | 1.21× |
| 8× | 18.1 | 0.89× |