← Back to community benchmarks
Qwen2.5-Coder-1.5B-Instruct
Performance
1k
tokens
1,055
PP tok/s
95.3
TG tok/s
970
TTFT (ms)
1.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,055 | 95.3 | 1.5 GB | current |
| 4k | 1,039 | 84.0 | 1.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 95.3 | 1.00× |
| 2× | 174.1 | 1.83× |
| 4× | 230.7 | 2.42× |