Local AI · Models

Run a useful AI on an old PC (8GB RAM, no big graphics card) with LFM3 in Ollama

Updated Nov 10, 2026 · By Blake, AI Pick Vault · Jump to comparison

Cheapest upgrade for an 8GB desktop: a 16GB DDR4 kit (2x8GB).See the price on Amazon

Affiliate note: as an Amazon Associate I earn from qualifying purchases, at no extra cost to you. Prices change constantly, so we do not list them. Click through for the current price.

Free tool

Will AI run on my PC? Check in 1 minute.

Our free tool looks at your computer and tells you, in plain words, what AI it can run today and the one thing to add if it needs help. Nothing to download. Nothing leaves your PC.

Check my PC →

Quick pick: short on time?

Cheapest upgrade16GB DDR4 desktop RAM kit (2x8GB)Doubles an 8GB desktop so the model, Windows and your browser all fit.
Check price on Amazon
Laptop with slots16GB DDR4 laptop SO-DIMM kit (2x8GB)Same idea for laptops. Check that the RAM is not soldered first.
Check price on Amazon
Still on a hard drive?1TB 2.5 inch SATA SSDModels and Windows load much faster than from a spinning drive.
Check price on Amazon

Side by side

Comparison at a glance

Your old PCCheap upgradeWhat it gets youPrice
8GB desktop (DDR4)16GB DDR4 kit (2x8GB)Room for 7B to 8B models plus a browserCheck price
8GB desktop (older DDR3)16GB DDR3 kit (2x8GB)Same, if the board supports 16GBCheck price
8GB laptop with RAM slots16GB DDR4 SO-DIMM kitSame, for laptops that are not solderedCheck price
Boots from a hard drive1TB SATA SSDFaster model loading and a snappier PCCheck price

Short answer: yes, an old Windows PC with 8GB of RAM and no big graphics card can run a useful AI for free. Install Ollama, then type ollama run lfm3. LFM3 1.7B is a small text model from Liquid AI (released Oct 27, 2026). Its default Ollama download is about 1.1GB, Liquid says it takes about 1GB of memory at 4-bit, and it has a 256K token context window and tool calling. It is good for short emails, summaries, rewrites and simple questions. It is not built for coding or hard multi step reasoning. Speed depends on your CPU.

Every spec below comes from Ollama's LFM3 page, Liquid AI's LFM3 announcement and Liquid AI's LFM3 1.7B model card, checked Nov 10, 2026. We did not benchmark it on a test PC, so there are no speed numbers here, only what to expect. No prices either. Click through for the current price.

Why an old PC is worth a try right now

RAM and graphics cards have gotten a lot more expensive in recent months. So before you buy anything, it makes sense to see what the PC you already own can do. Small models like LFM3 are made for exactly this: phones, laptops and ordinary desktops, not expensive AI workstations. If you are not sure what your PC has, run our free Check My PC tool first.

What LFM3 is (verified specs)

SpecLFM3 1.7B (text)Source
MakerLiquid AI. Announced Oct 27, 2026 as the first release of the LFM3 familyLiquid AI
Parameters1.73 billionLiquid AI / Ollama
Memory at 4-bitAbout 1GB ("fits on any phone or laptop")Liquid AI / Ollama
Context window256K tokens (input plus output)Liquid AI / Ollama
DesignTri-hybrid: 24 layers, 13 gated short convolutions, 5 sliding window attention, 6 global attentionLiquid AI
Built forLocal agents, tool calling, structured outputs, fine tuning for one jobLiquid AI
Not recommended forAgentic coding or complex multi step reasoning (its small size)Liquid AI
LanguagesEnglish, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, PolishLiquid AI
LicenseLFM Open License v1.0 (open weights)Liquid AI
FamilyBase, text, vision, audio, omni and decision models share one backbone. Ollama's lfm3 page lists the text model (text input)Liquid AI / Ollama

Which LFM3 download to pick in Ollama

Ollama lists these tags for lfm3 (sizes as shown on the Ollama tags page, Nov 10, 2026). On an old 8GB Windows PC, just use the default.

TagDownload sizeUse it when
lfm3 or lfm3:1.7b (default)1.1GB (listed as 1.1GB to 1.7GB)Start here. Best fit for 8GB PCs
lfm3:1.7b-q4_K_M1.1GBSame 4-bit size, pinned by name
lfm3:1.7b-qad-q4_01.0GBThe smallest tag, for the tightest PCs
lfm3:1.7b-q8_01.8GBA bit more accurate, needs more memory
lfm3:1.7b-bf163.5GBFull precision. Too heavy for most 8GB PCs
-mlx-bf16, -mxfp8, -nvfp43.5GB / 2.1GB / 1.7GBMarked MLX on Ollama. Skip these on an old Windows PC

Will it fit in 8GB?

Yes, with room to spare for the model itself. Windows and your browser already use a good share of 8GB, so the about 1GB model plus its working memory is what makes LFM3 a comfortable fit where a 7B or 8B model (around 5GB) would be tight. Two things to know:

For the full math on memory, see how much RAM and VRAM Ollama needs.

Set it up in 5 steps

  1. Check your PC. Task Manager > Performance shows your RAM and whether you have a graphics card. Ollama needs Windows 10 22H2 or newer, Home or Pro, and at least 4GB of free disk space for the program, plus room for models (Ollama's Windows page). The installer does not need administrator rights.
  2. Install or update Ollama. LFM3 is brand new, so an old copy of Ollama may not know it. Get the latest installer from ollama.com. Our Windows install guide walks through it.
  3. Download and chat. Open PowerShell or Command Prompt and type ollama run lfm3. The first run downloads about 1.1GB, then a chat prompt appears.
  4. See where it runs. In a second window, type ollama ps. It shows how much memory the model uses and whether it is on the CPU or a GPU.
  5. Keep answers steady. Liquid AI's model card suggests low randomness settings (temperature 0.1, top_k 50, repetition penalty 1.1). Small models do better with clear, short instructions and the text pasted in.

What to expect for speed (honest version)

We have not timed LFM3 on a real old Windows PC, so we will not give you a tokens per second number. Here is what is safe to say:

Good jobs for LFM3 on an old PC

Where it falls short

Backup small models that also fit 8GB

If LFM3 does not suit you, these small models are on Ollama too (default download sizes from each Ollama tags page, Nov 10, 2026). Try one, keep the one you like, and delete the rest with ollama rm.

ModelOllama commandDownloadNotes
Gemma 3 1B (Google)ollama run gemma3:1b806MBThe lightest option here
Llama 3.2 1B (Meta)ollama run llama3.2:1b1.3GBTiny and simple
Qwen 3 1.7B (Alibaba)ollama run qwen3:1.7b1.4GBSame size class as LFM3
Llama 3.2 3B (Meta)ollama run llama3.2:3b2.0GBA classic old PC pick
Qwen 3 4B (Alibaba)ollama run qwen3:4b2.5GBBigger, a bit smarter, slower
Gemma 3 4B (Google)ollama run gemma3:4b3.4GBCan also look at images. Tight on 8GB

New to model names? What is Ollama? The AI models explained covers what the "b" numbers mean in plain words.

When an upgrade is worth it

More guides live on the Local AI hub.

FAQ

Can a PC with 8GB of RAM run AI?

Yes, if you pick a small model. LFM3 1.7B downloads at about 1.1GB in Ollama's default tag, and Liquid AI says it needs about 1GB of memory at 4-bit precision. That leaves room for Windows on an 8GB PC. Close extra browser tabs while it runs.

Do I need a graphics card to run LFM3?

No. Ollama runs models on the CPU when there is no supported graphics card. Replies come out slower than on a GPU, and how fast depends on your processor, but a small 1.7B model is the kind of model that stays usable on CPU alone.

What is LFM3 good at?

Liquid AI built LFM3 1.7B for local agents, tool calling, structured outputs like lists and forms, and fine tuning for one job. In everyday terms: drafting short emails, rewriting or summarizing text you paste in, and simple questions. Liquid says to pair it with search or your own documents for fact heavy questions.

What should I not use LFM3 for?

Liquid AI says it is not recommended for agentic coding or complex multi step reasoning because of its small size. For coding or harder problems, a 7B to 8B model on 16GB of RAM, or a PC with a 12GB graphics card, is a better fit.

Does LFM3 really have a 256K context window?

Yes, Liquid AI and Ollama both list 256K tokens. But Ollama starts with a smaller default (4K tokens on machines with under 24GB of graphics memory) and a longer context uses more memory. On an 8GB PC, keep the default and paste in only what you need.

Ready to buy?

16GB DDR4 desktop RAM kit (2x8GB)Doubles an 8GB desktop so the model, Windows and your browser all fit.
Check price on Amazon
16GB DDR4 laptop SO-DIMM kit (2x8GB)Same idea for laptops. Check that the RAM is not soldered first.
Check price on Amazon
1TB 2.5 inch SATA SSDModels and Windows load much faster than from a spinning drive.
Check price on Amazon

Who picks these: Blake, the guy behind AI Pick Vault. 47 years of hands-on fixing things and troubleshooting PCs. These picks come from what actually fits in memory and what is least likely to cause headaches on a normal Windows PC, not from lab benchmarks.

No brand pays for placement. Amazon links are affiliate links.

16GB DDR4 desktop RAM kit (2x8GB)Check price on Amazon