← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
30.7
PP tok/s
5.0
TG tok/s
133352
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 30.7 | 5.8 | 15.7 GB | view |
| 4k | 30.7 | 5.0 | 16.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.8 | 1.00× |
| 2× | 5.2 | 0.90× |
| 4× | 4.0 | 0.69× |