← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
389.1
PP tok/s
39.1
TG tok/s
2632
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
96 GB
GPU Cores
80
Software
oMLX
v0.2.10
macOS
macOS 15.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 389.1 | 39.1 | 15.8 GB | current |
| 4k | 417.8 | 36.5 | 16.1 GB | view |
| 8k | 417.8 | 34.9 | 16.6 GB | view |
| 16k | 406.8 | 31.3 | 17.5 GB | view |
| 32k | 381.8 | 26.3 | 19.2 GB | view |
| 64k | 333.8 | 18.1 | 22.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.1 | 1.00× |
| 2× | 69.9 | 1.79× |
| 4× | 90.5 | 2.31× |
| 8× | 104.3 | 2.67× |