← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
429.3
PP tok/s
12.7
TG tok/s
9541
TTFT (ms)
23.6
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.20.dev3
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 388.5 | 12.9 | 22.1 GB | view |
| 4k | 429.3 | 12.7 | 23.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.9 | 1.00× |
| 2× | 22.7 | 1.76× |
| 4× | 28.1 | 2.18× |