← Back to community benchmarks
Qwen3.5-27B-mxfp8
Performance
4k
tokens
212.5
PP tok/s
15.7
TG tok/s
19275
TTFT (ms)
28.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 203.3 | 15.9 | 28.4 GB | view |
| 4k | 212.5 | 15.7 | 28.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.9 | 1.00× |
| 2× | 22.8 | 1.43× |
| 4× | 24.3 | 1.53× |