← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
914.6
PP tok/s
30.7
TG tok/s
4479
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.1
macOS
macOS 26.5.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 777.5 | 31.6 | 15.8 GB | view |
| 4k | 914.6 | 30.7 | 17.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.6 | 1.00× |
| 2× | 57.7 | 1.83× |
| 4× | 75.7 | 2.40× |