← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
8k
tokens
199.2
PP tok/s
7.8
TG tok/s
41128
TTFT (ms)
17.8
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 196.0 | 8.2 | 15.8 GB | view |
| 4k | 203.5 | 8.0 | 17.2 GB | view |
| 8k | 199.2 | 7.8 | 17.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.2 | 1.00× |
| 2× | 16.8 | 2.05× |
| 4× | 18.4 | 2.24× |