StarCoder 2 3B — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated February 28, 2024

Model library → StarCoder 2 → StarCoder 2 3B

Tiny but capable code completion model. Best used as a coding copilot in your editor via continue.dev or similar. Excellent for autocomplete with minimal VRAM.

StarCoder 2 3B needs about 3 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters3 Billion
Context window16,384
ArchitectureDense
ProviderBigCode
LicenceBigCode Open RAIL-M v1
Specified atQ4_K_M
System RAM8 GB
Record updated2024-02-28

Licence

BigCode OpenRAIL-M — commercial use permitted. Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), at 8K context. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K1.0 GB2.0 GB~269 tok/s (est.)Fits comfortably
Q3_K_M1.3 GB2.3 GB~244 tok/s (est.)Fits comfortably
Q4_K_M1.8 GB2.9 GB~208 tok/s (est.)Fits comfortably
Q5_K_M2.1 GB3.2 GB~191 tok/s (est.)Fits comfortably
Q6_K2.5 GB3.5 GB~176 tok/s (est.)Fits comfortably
Q8_03.2 GB4.2 GB~151 tok/s (est.)Fits comfortably
F166.0 GB7.1 GB~97 tok/s (est.)Fits comfortably

Want the memory numbers alone, at every quantization level and your own context length? Use the StarCoder 2 3B VRAM calculator.

Buy This HardwareIntel Arc B570 10GB — 10 GB VRAM · 150 W board powerDeploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs StarCoder 2 3B is the Intel Arc B570 (10 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run StarCoder 2 3B

Install Ollama, then run:

ollama run starcoder2:3b

Weights on Hugging Face: bigcode/starcoder2-3b.

Best for: code completion, editor plugin, low vram.

Can I Run StarCoder 2 3B on My GPU?

Other StarCoder 2 Sizes

StarCoder 2 3B — Frequently Asked Questions

How much VRAM does StarCoder 2 3B need?
About 3 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does StarCoder 2 3B run on an RTX 4090 (24 GB)?
Yes. StarCoder 2 3B needs about 3 GB at Q4_K_M, inside a 24 GB card, at an estimated 208 tokens/sec.
How do I run StarCoder 2 3B locally?
Install Ollama and run `ollama run starcoder2:3b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does StarCoder 2 come in?
StarCoder 2 3B (3 GB), StarCoder 2 7B (5 GB), StarCoder 2 15B (10 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All StarCoder 2 models | VRAM calculator | Check your own hardware