← Back to community benchmarks
Qwen2.5-Coder-7B-Instruct
Performance
4k
tokens
251.0
PP tok/s
20.9
TG tok/s
16317
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 255.7 | 23.0 | 4.5 GB | view |
| 4k | 251.0 | 20.9 | 4.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.0 | 1.00× |
| 2× | 46.4 | 2.02× |
| 4× | 58.1 | 2.53× |