← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
177.2
PP tok/s
22.9
TG tok/s
23121
TTFT (ms)
23.6
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
64 GB
GPU Cores
60
Software
oMLX
v0.3.0
macOS
macOS 15.3.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 170.1 | 24.3 | 22.1 GB | view |
| 4k | 177.2 | 22.9 | 23.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.3 | 1.00× |
| 2× | 30.5 | 1.26× |
| 4× | 33.7 | 1.39× |