← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-qx64-hi
Performance
1k
tokens
231.4
PP tok/s
23.1
TG tok/s
4426
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 231.4 | 23.1 | 19.9 GB | current |
| 4k | 235.4 | 22.2 | 20.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.1 | 1.00× |
| 2× | 40.7 | 1.76× |
| 4× | 46.8 | 2.03× |