← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
8k
tokens
65.6
PP tok/s
7.6
TG tok/s
124889
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 65.7 | 8.0 | 15.7 GB | view |
| 4k | 66.4 | 7.9 | 16.1 GB | view |
| 8k | 65.6 | 7.6 | 16.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.0 | 1.00× |
| 2× | 16.7 | 2.09× |
| 4× | 23.0 | 2.88× |