← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
62.7
PP tok/s
4.5
TG tok/s
16333
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 15.7.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 62.7 | 4.5 | 20.0 GB | current |
| 4k | 62.8 | 5.3 | 20.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 4.5 | 1.00× |
| 2× | 13.5 | 3.00× |
| 4× | 16.2 | 3.60× |
| 8× | 16.1 | 3.58× |