← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2
Performance
1k
tokens
61.4
PP tok/s
6.2
TG tok/s
16683
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.5
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 61.4 | 6.2 | 15.8 GB | current |
| 4k | 57.9 | 6.3 | 17.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.2 | 1.00× |
| 2× | 12.6 | 2.03× |
| 4× | 15.5 | 2.50× |