← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
58.1
PP tok/s
6.1
TG tok/s
70468
TTFT (ms)
17.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 61.3 | 6.3 | 15.8 GB | view |
| 4k | 58.1 | 6.1 | 17.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.3 | 1.00× |
| 2× | 12.3 | 1.95× |
| 4× | 15.3 | 2.43× |