← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
108.1
PP tok/s
10.7
TG tok/s
37892
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 104.4 | 11.5 | 15.8 GB | view |
| 4k | 108.1 | 10.7 | 16.1 GB | current |
| 8k | 109.4 | 10.8 | 16.6 GB | view |
| 16k | 100.5 | 9.5 | 17.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.5 | 1.00× |
| 2× | 17.6 | 1.53× |
| 4× | 25.5 | 2.22× |
| 8× | 27.2 | 2.37× |