← Back to community benchmarks
Qwen2.5-Coder-14B-Instruct
Performance
1k
tokens
114.0
PP tok/s
10.7
TG tok/s
8981
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 114.0 | 10.7 | 8.4 GB | current |
| 4k | 114.9 | 10.8 | 9.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.7 | 1.00× |
| 2× | 20.7 | 1.93× |
| 4× | 26.8 | 2.50× |