A DEVICETERRA PRODUCT

Practical technology for businesses and institutions.

Explore Deviceterra ↗
← RAM and hardware calculator
TESTED LOCALLENS HARDWARE PROFILE

Best Coding Models for a Computer With 8GB RAM

Find small coding models that can run locally on an 8GB computer without a dedicated GPU.

QUICK ANSWER

Yes. A computer with 8GB RAM can run small local AI models. A safe first choice from the current LocalLens list is Qwen 2.5 Coder 1.5B. This is a memory-fit estimate, not a speed promise.

The device we checked

System RAM8 GB
GraphicsNo dedicated GPU / not sure
WorkloadCoding
ContextAbout 2K

LocalLens keeps 3GB for the operating system and background work. That leaves a working model budget of about 5GB.

Best models to start with

#1 · Safe to test

Qwen 2.5 Coder 1.5B

Code-specific models for generation, fixing, explanation and code reasoning.

Estimated total RAM
5 GB
RAM left
3 GB
Expected path
CPU-only assumption
ollama run qwen2.5-coder:1.5bOpen verified model profile →
#2 · Safe to test

Qwen 2.5 Coder 3B

Code-specific models for generation, fixing, explanation and code reasoning.

Estimated total RAM
6 GB
RAM left
2 GB
Expected path
CPU-only assumption
ollama run qwen2.5-coder:3bOpen verified model profile →
#3 · Safe to test

Qwen 3 4B

A widely used hybrid reasoning family with tool support and multilingual strength.

Estimated total RAM
7 GB
RAM left
1 GB
Expected path
CPU-only assumption
ollama run qwen3:4bOpen verified model profile →

Recommended inference engine

LM Studio or Ollama

A CPU-first setup is the safest assumption when dedicated GPU support is unknown.

CPU use is practical for small models, but speed must be tested.

How accurate is this result?

This page uses the same calculator rules as the live LocalLens tool. It includes the selected model file, runtime overhead, operating-system reserve and context reserve. It does not claim a generation speed because processor generation, memory bandwidth, cooling, runtime settings and open applications change real performance.

Start with the first model. Test a normal task, check response speed and watch memory use before using it for important work.

Enter your exact hardware →

Other common hardware checks