← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
146.6
PP tok/s
11.6
TG tok/s
27940
TTFT (ms)
23.4
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
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 151.4 | 8.1 | 22.1 GB | view |
| 4k | 146.6 | 11.6 | 23.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.1 | 1.00× |
| 2× | 15.4 | 1.90× |
| 4× | 16.0 | 1.98× |