Runyard is a free hardware-aware AI model browser. You enter your CPU, GPU, and VRAM and it instantly shows every local LLM that will run on your machine, ranked by speed and quality.

How much VRAM do I need to run local LLMs?

8GB of VRAM runs 7B models like Llama 3.1 8B and Mistral 7B at Q4 quantization. 16GB unlocks 13B models. 24GB lets you run Mixtral 8x7B and Llama 3 70B at lower quantization.

What is the best local LLM for my GPU?

Use Runyard at www.runyard.dev — enter your GPU and VRAM and the Model Radar will rank every compatible LLM for your exact hardware, showing estimated tokens per second for each model.

Can I run Llama 3 locally?

Yes. Llama 3.1 8B at Q4 runs on any 8GB VRAM GPU. Llama 3.1 70B needs around 40GB VRAM at Q4, or an Apple Silicon Mac with 64GB+ unified memory.

Context Window Memory Calculator

P-02

Model size

Quantization

GPU or unified memory

System RAM

Context target

Quality preference

Speed preference

TurboQuant KV compression

Live result

5.59 GB estimated

P-02

Context Window Memory Calculator puts this setup around 5.59 GB including rough runtime overhead.

Weights

-4.50 GB

Q4_K_M

KV cache

-0.29 GB

8K context

How It Works

3 inputs. Instant results.

01

Set the scenario

Choose realistic hardware, model, and context assumptions.

02

Read the result

The hero shows a working result instead of a decorative promo block.

03

Act on the outcome

Use the result to adjust fit, speed, quantization, or context.

Features

Everything that powers context window memory calculator.

01

Planning-first

Built to make local-AI decisions easier to reason about.

02

Local-AI focused

Built to make local-AI decisions easier to reason about.

03

Interactive hero

Built to make local-AI decisions easier to reason about.

04

Runyard design system

Built to make local-AI decisions easier to reason about.

05

Target model size

Grounded in the actual inputs and outputs this page is designed around.

06

KV cache growth curve

Grounded in the actual inputs and outputs this page is designed around.

07

Built for long chat and RAG use cases

Grounded in the actual inputs and outputs this page is designed around.

08

Standalone tool

Grounded in the actual inputs and outputs this page is designed around.

Spotlight

The differentiator behind context window memory calculator.

KV at 8K context

Unknown cost~0.3 GB7B Q4 baseline

KV at 32K context

0.3 GB~1.2 GB4× growth

KV at 128K context

Guessing~4.8 GBPlan this ahead

Visual comparison

Clarity

Fit

Actionability

Reading Results

How to read the output tiers.

Comfortable

<70%

Enough breathing room for normal use.

Tight

70%-95%

Should work, but overhead matters.

Borderline

95%-110%

Likely needs one tradeoff.

Too heavy

>110%

Time to step down.

Quick Reference

Common setups at useful defaults.

Scenario	Baseline	Result	Notes
Starter setup	7B / Q4 / 8K	Light local target	Good first benchmark
Balanced setup	8B / Q4 / 16K	Everyday sweet spot	Works for many users
Heavier setup	14B / Q5 / 16K	Quality-focused target	Needs stronger hardware
Stretch setup	32B / Q4 / 16K	Ambitious local target	Useful upper bound

* These are approximations for planning, not a promise of exact runtime behavior.

Benefits

Why people use context window memory calculator.

01

Faster decisions

It helps eliminate dead-end local AI choices before you download, benchmark, or configure too much.

02

Clearer tradeoffs

The page turns a raw estimate into something you can actually act on.

03

Useful on its own

The hero provides a working tool surface while the rest of the page explains what the output means.

FAQ

Questions people ask before using context window memory calculator.

How does context window size affect memory?

KV cache grows linearly with context length. At 8K it adds a few hundred MB. At 64K–128K it often exceeds model weight cost — a 7B model at Q4 needs ~0.3 GB KV at 8K but ~4.8 GB at 128K.

What is KV cache and why does it matter?

KV (key-value) cache stores attention patterns for each token in the active context. It accumulates as conversation grows and is the main reason long-context inference costs more VRAM than a simple model load.

When does context become the real bottleneck?

Typically past 16K tokens. At that point, KV cache starts competing with model weights for available VRAM. At 128K, the cache alone can exceed model weights for most consumer GPUs.

Does this apply to Ollama's num_ctx setting?

Yes. Ollama's num_ctx maps directly to the context window. Setting num_ctx=32768 uses significantly more memory than the default 2048 — sometimes enough to cause silent failures on limited hardware.

How much more memory does 128K context need vs 8K?

Roughly 16× more KV cache. A 7B model at Q4 uses ~0.3 GB KV at 8K and ~4.8 GB at 128K. On a 12 GB GPU, that difference can push a setup over the edge.

Should I always maximise context length?

No. Set it to what the task actually needs. Chat sessions rarely exceed 8K–16K. Long RAG or code review sessions may justify 32K. 128K is expensive and rarely fully utilised locally.

RUNYARD.DEV / Tools / Context Window Memory Calculator

Estimates on this page are directional and should be validated against your actual runtime and hardware.