← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
111.6
PP tok/s
21.3
TG tok/s
9179
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
64 GB
GPU Cores
38
Software
oMLX
v0.2.7
macOS
macOS 15.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 111.6 | 21.3 | 15.8 GB | current |
| 4k | 113.8 | 20.0 | 16.1 GB | view |
| 8k | 113.1 | 19.1 | 16.6 GB | view |
| 16k | 111.0 | 17.2 | 17.5 GB | view |
| 32k | 106.7 | 15.2 | 19.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.3 | 1.00× |
| 2× | 28.2 | 1.32× |
| 4× | 30.0 | 1.41× |
| 8× | 20.6 | 0.97× |