OLMo 2 13B Instruct — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated November 26, 2024

Model library → OLMo 2 → OLMo 2 13B Instruct

The larger OLMo 2 variant. Beats Llama 3.1 8B on most academic benchmarks while maintaining full data and code transparency. Ideal for NLP research institutions.

OLMo 2 13B Instruct needs about 9 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

Parameters13 Billion
Context window4,096
ArchitectureDense
ProviderAllen AI
LicenceApache 2.0
Specified atQ4_K_M
System RAM24 GB
Record updated2024-11-26

Licence

Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

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_K4.5 GB12.0 GB~79 tok/s (est.)Fits comfortably
Q3_K_M5.8 GB13.4 GB~69 tok/s (est.)Fits comfortably
Q4_K_M8.3 GB15.8 GB~57 tok/s (est.)Fits comfortably
Q5_K_M9.7 GB17.2 GB~51 tok/s (est.)Fits comfortably
Q6_K11.2 GB18.7 GB~46 tok/s (est.)Fits comfortably
Q8_014.6 GB22.1 GB~39 tok/s (est.)Tight fit
F1627.4 GB34.9 GB~3 tok/s (est.)Offloads to system RAM (slow)

Want the memory numbers alone, at every quantization level and your own context length? Use the OLMo 2 13B Instruct 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 OLMo 2 13B Instruct 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 OLMo 2 13B Instruct

Install Ollama, then run:

ollama run olmo2:13b

Weights on Hugging Face: allenai/OLMo-2-1124-13B-Instruct.

Best for: research, education, rag.

Can I Run OLMo 2 13B Instruct on My GPU?

Other OLMo 2 Sizes

OLMo 2 13B Instruct — Frequently Asked Questions

How much VRAM does OLMo 2 13B Instruct need?
About 9 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 OLMo 2 13B Instruct run on an RTX 4090 (24 GB)?
Yes. OLMo 2 13B Instruct needs about 9 GB at Q4_K_M, inside a 24 GB card, at an estimated 57 tokens/sec.
How do I run OLMo 2 13B Instruct locally?
Install Ollama and run `ollama run olmo2:13b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does OLMo 2 come in?
OLMo 2 7B Instruct (5 GB), OLMo 2 13B Instruct (9 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

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