← Back to community benchmarks

DeepSeek-Coder-V2-Lite-Instruct-4bit

M2 Max (30c) · 64 GB · 4bit · 2026-04-28
Performance
4k
tokens
1,256
PP tok/s
75.9
TG tok/s
3267
TTFT (ms)
10.2
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 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,166 110.8 9.2 GB view
4k 1,256 75.9 10.2 GB current
Batching Results
Batch Size TG tok/s Speedup
110.8 1.00×
141.3 1.28×
169.9 1.53×