← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
306.2
PP tok/s
40.4
TG tok/s
3344
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.4.4rc1
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 306.2 | 40.4 | 15.8 GB | current |
| 4k | 321.3 | 38.7 | 17.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.4 | 1.00× |
| 2× | 63.3 | 1.57× |
| 4× | 72.5 | 1.79× |
| 8× | 82.0 | 2.03× |