← Back to community benchmarks
Qwen2.5-0.5B-Instruct
Performance
4k
tokens
2,980
PP tok/s
81.0
TG tok/s
1374
TTFT (ms)
1.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,498 | 89.7 | 1.3 GB | view |
| 4k | 2,980 | 81.0 | 1.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 89.7 | 1.00× |
| 2× | 115.1 | 1.28× |
| 4× | 212.0 | 2.36× |