← Back to community benchmarks
Qwen3.5-27B-Text-heretic-mxfp4
Performance
4k
tokens
53.7
PP tok/s
6.6
TG tok/s
76327
TTFT (ms)
15.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 54.4 | 6.8 | 14.9 GB | view |
| 4k | 53.7 | 6.6 | 15.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.8 | 1.00× |
| 2× | 11.2 | 1.65× |
| 4× | 8.0 | 1.18× |