← Back to community benchmarks
DeepSeek-Coder-V2-Lite-Instruct-4bit
Performance
1k
tokens
1,232
PP tok/s
110.6
TG tok/s
835
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 | 1,232 | 110.6 | 9.2 GB | current |
| 4k | 1,279 | 75.6 | 10.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 110.6 | 1.00× |
| 2× | 145.0 | 1.31× |
| 4× | 170.2 | 1.54× |