← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
8k
tokens
117.1
PP tok/s
10.9
TG tok/s
69933
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 110.4 | 11.8 | 15.8 GB | view |
| 4k | 121.6 | 11.4 | 16.1 GB | view |
| 8k | 117.1 | 10.9 | 16.6 GB | current |
| 16k | 114.5 | 9.5 | 17.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.8 | 1.00× |
| 2× | 19.9 | 1.69× |
| 4× | 24.4 | 2.07× |
| 8× | 28.7 | 2.43× |