DeepSeek Coder v2 Lite Base vs DeepSeek Coder v2 Lite Instruct

Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.

DeepSeek Coder v2 Lite Base

DeepSeek · 15.7B

ChatCode
DeepSeek Coder v2 Lite Instruct

DeepSeek · 15.7B

ChatCode

Specifications

DeepSeek Coder v2 Lite BaseDeepSeek Coder v2 Lite Instruct
Parameters15.7B15.7B
Context164K164K
ArchitectureDeepseekV2ForCausalLMDeepseekV2ForCausalLM
LicenseOtherOther
Downloads4.8K877.2K
ReleasedJul 2024Jul 2024

VRAM by Quantization: DeepSeek Coder v2 Lite Base vs DeepSeek Coder v2 Lite Instruct

QuantizationBitsDeepSeek Coder v2 Lite Base VRAMDeepSeek Coder v2 Lite Instruct VRAM
Q2_K3.407.4 GB
Q3_K_M3.908.4 GB
Q3_K_S3.507.6 GB
Q4_04.008.6 GB
Q4_K_M4.8010.2 GB
Q5_K_M5.7011.9 GB
Q6_K6.6013.7 GB
Q8_08.0016.5 GB

Verdict

DeepSeek Coder v2 Lite Instruct is the more widely downloaded of the two.

Frequently Asked Questions

Which has a longer context window, DeepSeek Coder v2 Lite Base or DeepSeek Coder v2 Lite Instruct?

DeepSeek Coder v2 Lite Base supports 163,840 tokens and DeepSeek Coder v2 Lite Instruct supports 163,840 tokens.

What is the difference between DeepSeek Coder v2 Lite Base and DeepSeek Coder v2 Lite Instruct?

DeepSeek Coder v2 Lite Base is a 15.7B model from DeepSeek (DeepSeek Coder family), while DeepSeek Coder v2 Lite Instruct is a 15.7B model from DeepSeek (DeepSeek Coder family). Compare their VRAM requirements above to see which fits your GPU or Mac.