← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-6bit
Performance
4k
tokens
61.4
PP tok/s
4.8
TG tok/s
66673
TTFT (ms)
22.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 60.5 | 4.8 | 21.9 GB | view |
| 4k | 61.4 | 4.8 | 22.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 4.8 | 1.00× |
| 2× | 9.3 | 1.94× |
| 4× | 9.5 | 1.98× |