← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
240.5
PP tok/s
27.5
TG tok/s
17030
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.2.8
macOS
macOS 15.6.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 236.2 | 28.9 | 15.8 GB | view |
| 4k | 240.5 | 27.5 | 16.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.9 | 1.00× |
| 2× | 53.2 | 1.84× |
| 4× | 53.5 | 1.85× |