← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
319.0
PP tok/s
36.6
TG tok/s
12838
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 303.7 | 38.3 | 15.8 GB | view |
| 4k | 319.0 | 36.6 | 16.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.3 | 1.00× |
| 2× | 62.8 | 1.64× |
| 4× | 71.9 | 1.88× |