← Back to community benchmarks
Qwen2.5-Coder-14B-Instruct
Performance
1k
tokens
96.8
PP tok/s
9.9
TG tok/s
10574
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 96.8 | 9.9 | 8.4 GB | current |
| 4k | 94.3 | 7.7 | 9.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.9 | 1.00× |
| 2× | 14.7 | 1.48× |