← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
65.8
PP tok/s
8.0
TG tok/s
15558
TTFT (ms)
15.7
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 65.8 | 8.0 | 15.7 GB | current |
| 4k | 64.9 | 7.9 | 16.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.0 | 1.00× |
| 2× | 16.4 | 2.05× |
| 4× | 21.9 | 2.74× |