← Back to community benchmarks
DeepSeek-Coder-V2-Lite-Instruct-4bit
Performance
1k
tokens
1,146
PP tok/s
61.8
TG tok/s
898
TTFT (ms)
9.0
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,146 | 61.8 | 9.0 GB | current |
| 4k | 1,282 | 40.0 | 10.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.8 | 1.00× |
| 2× | 78.6 | 1.27× |
| 4× | 84.4 | 1.37× |