← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-qx64-hi
Performance
128k
tokens
295.6
PP tok/s
7.5
TG tok/s
443401
TTFT (ms)
41.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 713.5 | 25.9 | 20.0 GB | view |
| 4k | 648.0 | 25.1 | 21.6 GB | view |
| 128k | 295.6 | 7.5 | 41.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.9 | 1.00× |
| 2× | 24.8 | 0.96× |
| 4× | 34.0 | 1.31× |