← Back to community benchmarks
DeepSeek-Coder-V2-Lite-Instruct-4bit
Performance
1k
tokens
1,166
PP tok/s
110.8
TG tok/s
882
TTFT (ms)
9.2
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
64 GB
GPU Cores
30
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,166 | 110.8 | 9.2 GB | current |
| 4k | 1,256 | 75.9 | 10.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 110.8 | 1.00× |
| 2× | 141.3 | 1.28× |
| 4× | 169.9 | 1.53× |