← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-qx64-hi
Performance
1k
tokens
88.3
PP tok/s
16.5
TG tok/s
11601
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
64 GB
GPU Cores
30
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 88.3 | 16.5 | 19.9 GB | current |
| 4k | 90.0 | 16.0 | 20.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.5 | 1.00× |
| 2× | 20.1 | 1.22× |
| 4× | 21.3 | 1.29× |