← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
62.7
PP tok/s
6.5
TG tok/s
65360
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.20rc1
macOS
macOS 15.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 62.5 | 6.5 | 15.8 GB | view |
| 4k | 62.7 | 6.5 | 17.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.5 | 1.00× |
| 2× | 13.0 | 2.00× |
| 4× | 16.1 | 2.48× |