← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
154.2
PP tok/s
16.8
TG tok/s
6643
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 154.2 | 16.8 | 15.8 GB | current |
| 4k | 147.5 | 16.4 | 16.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.8 | 1.00× |
| 2× | 30.7 | 1.83× |
| 4× | 24.1 | 1.43× |