← Back to community benchmarks
Qwen3.5-27B-mxfp8
Performance
1k
tokens
120.0
PP tok/s
8.8
TG tok/s
8533
TTFT (ms)
28.4
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.9
macOS
macOS 15.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 120.0 | 8.8 | 28.4 GB | current |
| 4k | 121.3 | 8.4 | 28.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.8 | 1.00× |
| 2× | 13.9 | 1.58× |