← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2
Performance
4k
tokens
98.7
PP tok/s
8.5
TG tok/s
41519
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
36 GB
GPU Cores
18
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 95.2 | 7.5 | 15.8 GB | view |
| 4k | 98.7 | 8.5 | 17.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.5 | 1.00× |
| 2× | 17.0 | 2.27× |
| 4× | 25.2 | 3.36× |