← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
8k
tokens
716.8
PP tok/s
29.9
TG tok/s
11428
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 744.9 | 30.8 | 15.8 GB | view |
| 4k | 777.8 | 28.0 | 17.3 GB | view |
| 8k | 716.8 | 29.9 | 18.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.8 | 1.00× |
| 2× | 52.1 | 1.69× |
| 4× | 53.0 | 1.72× |