← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
780.0
PP tok/s
32.8
TG tok/s
1313
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 780.0 | 32.8 | 15.8 GB | current |
| 4k | 897.1 | 31.9 | 17.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.8 | 1.00× |
| 2× | 60.3 | 1.84× |
| 4× | 76.5 | 2.33× |