Run your own AI · Model finder

Which open model runs on your machine?

Checked 6 November 2026. US dollars. No affiliate links.

Pick how much memory your computer has and the finder shows the models that fit. Every card says who made the model, what its license lets you do, who set its behavior, and the page each figure came from.

My machine has

License

Who set the behavior

Reads images

Showing 27 of 27.

Gemma 4 E2B
Fits 8GB
Google DeepMind · 2B effective parameters
Phones, old laptops, quick private chat
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text, Image, Audio
Context
128K
Download
2.9GB at 4-bit (Google's figure)
ollama run gemma4:e2b
Source · checked 6 November 2026 · Gemma 4 graded
Gemma 4 E4B
Fits 8GB
Google DeepMind · 4B effective parameters
The best first model for an 8GB machine
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text, Image, Audio
Context
128K
Download
4.5GB at 4-bit (Google's figure)
ollama run gemma4:e4b
Source · checked 6 November 2026 · Gemma 4 graded
Llama 3.2 3B
Fits 8GB
Meta · 3B parameters
Very old or very small machines
License
Llama 3.2 Community License
License rules
Acceptable Use Policy; very large services (700M+ monthly users) need Meta's permission
Behavior
Maker's own tuning
Reads
Text
Context
128K
Download
2.0GB
ollama run llama3.2:3b
Source · checked 6 November 2026
Llama 3.1 8B
Fits 8GB
Meta · 8B parameters
The most-downloaded base for community retunes
License
Llama 3.1 Community License
License rules
Acceptable Use Policy; very large services (700M+ monthly users) need Meta's permission
Behavior
Maker's own tuning
Reads
Text
Context
128K
Download
4.9GB
ollama run llama3.1:8b
Source · checked 6 November 2026
DeepSeek-R1-0528-Qwen3-8B
Fits 8GB
DeepSeek · 8B parameters
Step-by-step reasoning on a small machine (it thinks out loud, so it is slower)
License
MIT (built on Qwen3 8B)
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text
Context
128K
Download
5.2GB
ollama run deepseek-r1:8b
Source · checked 6 November 2026
Qwen3.5 9B
Fits 16GB
Alibaba (Qwen) · 9B parameters
All-round everyday model with vision and tool use
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text, Image
Context
256K
Download
6.6–7.6GB
Note
Loads on 8GB with little room left for long chats; 16GB is comfortable.
ollama run qwen3.5:9b
Source · checked 6 November 2026
Dolphin 3.0 8B
Fits 8GB
Cognitive Computations · 8B (Llama 3.1 8B base) parameters
A model that follows your system prompt rather than the maker's defaults
License
Llama 3.1 Community License (inherited)
License rules
Meta's Acceptable Use Policy still applies to a retune of Llama
Behavior
Community retune; its page says the system owner sets the guidelines
Reads
Text
Context
128K
Download
4.9GB
ollama run dolphin3
Source · checked 6 November 2026
Hermes 3 8B
Fits 8GB
Nous Research · 8B (Hermes-3-Llama-3.1-8B) parameters
Role-play, fiction and agents that should take direction from you
License
Llama 3.1 Community License (inherited)
License rules
Meta's Acceptable Use Policy still applies to a retune of Llama
Behavior
Community retune; Nous says it aligns the model to the user and gives the user strong steering
Reads
Text
Context
128K
Download
4.7GB
ollama run hermes3:8b
Source · checked 6 November 2026
Gemma 4 12B
Fits 16GB
Google DeepMind · 12B parameters
The sweet spot for a 16GB laptop: documents, images, writing
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text, Image
Context
256K
Download
6.7GB at 4-bit (Google's figure)
ollama run gemma4:12b
Source · checked 6 November 2026 · Gemma 4 graded
gpt-oss-20b
Fits 16GB
OpenAI · 21B parameters, 3.6B active
Reasoning and tool use, with adjustable thinking effort
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text
Context
128K
Download
14GB
Note
The maker says it runs within 16GB of memory; a 16GB laptop has little left over for other apps.
ollama run gpt-oss:20b
Source · checked 6 November 2026
Phi-4
Fits 16GB
Microsoft · 14B parameters
Logic and short reasoning tasks in English; short context
License
MIT
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text
Context
16K
Download
9.1GB
ollama run phi4
Source · checked 6 November 2026
Gemma 4 26B A4B
Fits 24–32GB
Google DeepMind · 26B parameters, 4B active
Fast on a 24GB card because only 4B parameters work per word
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text, Image
Context
256K
Download
14.4GB at 4-bit (Google's figure)
ollama run gemma4:26b
Source · checked 6 November 2026 · Gemma 4 graded
Gemma 4 31B
Fits 24–32GB
Google DeepMind · 31B parameters
Best Gemma quality that fits one 24GB card
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text, Image
Context
256K
Download
17.5GB at 4-bit (Google's figure)
ollama run gemma4:31b
Source · checked 6 November 2026 · Gemma 4 graded
Qwen3.8 27B
Fits 24–32GB
Alibaba (Qwen) · 27B parameters
The strongest all-rounder for a 24GB card, and coding agents
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text, Image, Video
Context
256K
Download
18GB
ollama run qwen3.8:27b
Source · checked 6 November 2026 · Qwen3.8 graded
Mistral Small 3.2 24B
Fits 24–32GB
Mistral AI · 24B parameters
European-made all-rounder with reliable function calling
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text, Image
Context
128K
Download
15GB
ollama run mistral-small3.2
Source · checked 6 November 2026
Nemotron 3.5 Lightning
Fits 24–32GB
NVIDIA · 30B parameters, 3B active
Long documents on a 32GB-plus graphics card
License
OpenMDW-1.1
License rules
Keep the agreement and notices; a patent-retaliation clause
Behavior
Maker's own tuning
Reads
Text
Context
Up to 1M (4K by default under 24GB)
Download
—
Note
NVIDIA lists RTX 5090 and DGX Spark; under 24GB Ollama defaults to a 4K context.
Source · checked 3 November 2026 · Nemotron graded
Olmo 3.1 32B
Fits 24–32GB
Ai2 · 32B parameters
The fully open choice: data, code and checkpoints are all published
License
Apache 2.0 · fully open (data and code too)
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text
Context
Not stated on the card
Download
—
Note
Our estimate: 32B at 4-bit needs about 18–20GB. Ai2 gives no figure.
Source · checked 6 November 2026 · Olmo graded
Devstral Small 2
Fits 24–32GB
Mistral AI · 24B parameters
Coding agents that explore and edit a whole codebase
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text, Image
Context
384K
Download
15GB
ollama run devstral-small-2
Source · checked 6 November 2026
Qwen3-Coder 30B A3B
Fits 24–32GB
Alibaba (Qwen) · 30B parameters, 3.3B active
Fast coding help on a 24GB card: only 3.3B parameters work per word
License
Not stated on the Ollama page; read the card
License rules
Not read yet: check the Hugging Face card before commercial use
Behavior
Maker's own tuning
Reads
Text
Context
256K
Download
19GB
ollama run qwen3-coder:30b
Source · checked 6 November 2026
Llama 3.3 70B
Fits 64–128GB
Meta · 70B parameters
A large dense model for a 64GB-plus Mac; slow on mini PCs
License
Llama 3.3 Community License
License rules
Acceptable Use Policy; very large services (700M+ monthly users) need Meta's permission
Behavior
Maker's own tuning
Reads
Text
Context
128K
Download
43GB
ollama run llama3.3
Source · checked 6 November 2026
gpt-oss-120b
Fits 64–128GB
OpenAI · 117B parameters, 5.1B active
Close to a hosted experience on a 128GB machine
License
Apache 2.0
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text
Context
128K
Download
65GB
Note
The maker targets one 80GB GPU; a 128GB Mac or mini PC runs it.
ollama run gpt-oss:120b
Source · checked 6 November 2026 · gpt-oss graded
Hermes 3 70B
Fits 64–128GB
Nous Research · 70B (Hermes-3-Llama-3.1-70B) parameters
A large steerable model for a 64GB-plus machine
License
Llama 3.1 Community License (inherited)
License rules
Meta's Acceptable Use Policy still applies to a retune of Llama
Behavior
Community retune; Nous says it aligns the model to the user and gives the user strong steering
Reads
Text
Context
128K
Download
40GB
ollama run hermes3:70b
Source · checked 6 November 2026
DeepSeek-V4.1-Flash
Server-size
DeepSeek · 552B parameters, 8–16B active
Frontier-class open model; rent it through a host or router
License
MIT
License rules
None beyond keeping the notices
Behavior
Maker's own tuning
Reads
Text
Context
1M
Download
—
Source · checked 3 November 2026 · DeepSeek V4 graded
GLM-5.3
Server-size
Z.ai · 753B parameters
Coding agents through a cheap plan or a router
License
GLM-5.3 License (MIT-style)
License rules
Very large model-as-a-service operators must pass Z.ai's security review
Behavior
Maker's own tuning
Reads
Text
Context
Not stated on the card
Download
—
Source · checked 3 November 2026 · GLM graded
Kimi K3
Server-size
Moonshot AI · 2.8T parameters, 104B active
Long agent runs through a host or router
License
Kimi K3 License (MIT-style)
License rules
Model-as-a-service businesses over $20M a year need a separate agreement
Behavior
Maker's own tuning
Reads
Text
Context
1M
Download
—
Source · checked 3 November 2026 · Kimi graded
Muse Spark Open
Server-size
Meta · 816B parameters, 42B active
Meta's newest open release; needs serious hardware
License
Muse Model License
License rules
"Built with Muse Spark Open" display, Usage Policy, and a $20M model-as-a-service clause; gated download
Behavior
Maker's own tuning
Reads
Text
Context
1M
Download
—
Note
Meta says it is optimized to run on two Mac Studios with M5 Ultra.
Source · checked 3 November 2026 · Muse graded
Mistral Large 4
Server-size
Mistral AI · About 1T parameters, 52B active
Research and personal use at frontier scale
License
Mistral Ecosystem Open-Weight License
License rules
Commercial operation needs a separate license from Mistral
Behavior
Maker's own tuning
Reads
Text
Context
1M
Download
—
Source · checked 3 November 2026 · Mistral Large graded

One page per sizeFits 8GB (7)Fits 16GB (11)Fits 24–32GB (19)Fits 64–128GB (22)Needs a server (5)

What the machine sizes mean

8GB: Most laptops, an 8GB Mac, an 8GB graphics card
16GB: A 16GB Mac or laptop, a 12–16GB graphics card
24–32GB: A 24GB graphics card, a 32GB Mac
64–128GB: A 64–128GB Mac Studio or 128GB mini PC
Server: Rented GPUs or a host: too big for one home machine

On a Mac, the memory is shared, so a 16GB Mac has 16GB for the model and everything else. On a PC, the graphics card's own memory (VRAM) is what counts for speed; a model that spills into ordinary RAM still runs, but slowly. More on that in model sizes and quantization.

How to read a card

Download is the default 4-bit build on Ollama, or the maker's own 4-bit memory figure where it publishes one. Leave a few gigabytes on top for the conversation itself.
License rules are the conditions the license adds. Apache 2.0 and MIT add almost none. Custom licenses can add usage policies, display rules and revenue caps.
Behavior says who tuned the model: the maker, or a community group that retuned the maker's model to follow your instructions instead of the maker's defaults. We have not measured how often any model refuses. The community's own attempt is the UGI Leaderboard; treat it as community data, not ours.
Graded links go to the open-models shelf, where the family is graded on license, weights, context, running it, price, training and fine-tuning, from the maker's own pages.

What is not here yet

This is the first cut: 27 models, chosen because they are current, popular on Ollama, or the strongest of their size. Coding-only models, image generators and speech models come next. If a model you use is missing, tell us through Work with Adam.

Gemma 4 E2B

Gemma 4 E4B

Llama 3.2 3B

Llama 3.1 8B

DeepSeek-R1-0528-Qwen3-8B

Qwen3.5 9B

Dolphin 3.0 8B

Hermes 3 8B

Gemma 4 12B

gpt-oss-20b

Phi-4

Gemma 4 26B A4B

Gemma 4 31B

Qwen3.8 27B

Mistral Small 3.2 24B

Nemotron 3.5 Lightning

Olmo 3.1 32B

Devstral Small 2

Qwen3-Coder 30B A3B

Llama 3.3 70B

gpt-oss-120b

Hermes 3 70B

DeepSeek-V4.1-Flash

GLM-5.3

Kimi K3

Muse Spark Open

Mistral Large 4

What the machine sizes mean

How to read a card

What is not here yet