← Back to community benchmarks
Qwen3.5-27B-mxfp8
Performance
4k
tokens
434.5
PP tok/s
10.0
TG tok/s
9426
TTFT (ms)
28.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 410.1 | 10.1 | 28.4 GB | view |
| 4k | 434.5 | 10.0 | 28.7 GB | current |
| 8k | 430.7 | 9.7 | 29.2 GB | view |
| 16k | 408.5 | 9.3 | 30.0 GB | view |
| 32k | 380.2 | 8.6 | 31.8 GB | view |
| 64k | 321.4 | 7.4 | 35.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.1 | 1.00× |
| 2× | 18.5 | 1.83× |
| 4× | 24.2 | 2.40× |
| 8× | 25.3 | 2.50× |