← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
63.2
PP tok/s
6.7
TG tok/s
64860
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 62.5 | 6.0 | 15.7 GB | view |
| 4k | 63.2 | 6.7 | 16.1 GB | current |
| 8k | 61.6 | 6.4 | 16.5 GB | view |
| 16k | 56.8 | 6.0 | 17.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.0 | 1.00× |
| 2× | 13.5 | 2.25× |
| 4× | 16.3 | 2.72× |