← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
65.0
PP tok/s
8.4
TG tok/s
15744
TTFT (ms)
15.7
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 65.0 | 8.4 | 15.7 GB | current |
| 4k | 66.1 | 8.1 | 16.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.4 | 1.00× |
| 2× | 16.2 | 1.93× |
| 4× | 18.7 | 2.23× |