← Back to community benchmarks
DeepSeek-Coder-V2-Lite-Instruct
Performance
4k
tokens
1,312
PP tok/s
39.9
TG tok/s
3126
TTFT (ms)
10.2
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,128 | 62.1 | 9.0 GB | view |
| 4k | 1,312 | 39.9 | 10.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.1 | 1.00× |
| 2× | 83.1 | 1.34× |
| 4× | 88.0 | 1.42× |