← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
111.4
PP tok/s
21.3
TG tok/s
9192
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
64 GB
GPU Cores
38
Software
oMLX
v0.2.6
macOS
macOS 15.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 111.4 | 21.3 | 15.8 GB | current |
| 32k | 106.7 | 15.1 | 19.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.3 | 1.00× |
| 2× | 28.3 | 1.33× |
| 4× | 30.0 | 1.41× |
| 8× | 20.6 | 0.97× |