← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-6bit-abliterated
Performance
4k
tokens
111.2
PP tok/s
10.0
TG tok/s
36833
TTFT (ms)
25.8
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.9
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 109.1 | 10.3 | 25.1 GB | view |
| 4k | 111.2 | 10.0 | 25.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.3 | 1.00× |
| 2× | 17.4 | 1.69× |
| 4× | 18.2 | 1.77× |