← Back to community benchmarks
HY-MT1.5-1.8B
Performance
32k
tokens
844.2
PP tok/s
42.3
TG tok/s
38814
TTFT (ms)
4.4
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.8
macOS
macOS 26.3
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,614 | 104.9 | 2.4 GB | view |
| 4k | 1,583 | 90.7 | 2.7 GB | view |
| 8k | 1,450 | 77.8 | 3.0 GB | view |
| 16k | 1,179 | 60.9 | 3.4 GB | view |
| 32k | 844.2 | 42.3 | 4.4 GB | current |
| 64k | 521.4 | 1.7 | 6.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 104.9 | 1.00× |
| 2× | 185.0 | 1.76× |
| 4× | 250.6 | 2.39× |
| 8× | 279.2 | 2.66× |