← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
169.6
PP tok/s
29.8
TG tok/s
6037
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
128 GB
GPU Cores
64
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 169.6 | 29.8 | 15.8 GB | current |
| 4k | 176.6 | 28.0 | 16.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.8 | 1.00× |
| 2× | 37.5 | 1.26× |
| 4× | 33.2 | 1.11× |