YOUR MEMORY BUDGET

Local AI models for 16GB VRAM.

Explore models by theoretical weight storage. This shortlist covers available downloadable language models with a known or name-derived parameter count.

14 GBleft for weights at 4-bit
16 GB budget − 2 GB reserve

The reserve is your assumption, not a measured overhead allowance. The default 2 GB may be too little for your runtime or context length. Results are not confirmed fits and have no verified speed rating. Weight estimates use decimal GB and do not include quantization overhead. For timed results on one 12GB machine, see measured speeds.

1,030 models within the weight budget

Largest parameter count first · not a quality ranking

Datalab · Downloadable

lift

Vision

Understands text and images and responds in text.

Source listed
Jun 19, 2026
Parameters
9.7B
4-bit weights only
≈ 4.8 GB
License
openrail
Compare this model →

OpenBMB · Downloadable

MiniCPM-SALA

Text generation

Generates text for conversations and writing.

Source listed
Feb 11, 2026
Parameters
9.5B
4-bit weights only
≈ 4.7 GB
License
apache-2.0
Compare this model →

Black Forest Labs · Downloadable

flux-3-image-klein-pup

VisionImage generationImage editing

Understands text and images and responds in text.

Source listed
Oct 14, 2026
Parameters
9.4B
4-bit weights only
≈ 4.7 GB
License
apache-2.0
Compare this model →

Cloudflare · Downloadable

clef-flash

Vision

Understands text and images and responds in text.

Source listed
Sep 30, 2026
Parameters
9.4B
4-bit weights only
≈ 4.7 GB
License
apache-2.0
Compare this model →

Moondream · Downloadable

moondream-next

Text generation

Generates text for conversations and writing.

Source listed
Apr 11, 2025
Parameters
9.3B
4-bit weights only
≈ 4.6 GB
License
Not disclosed
Compare this model →

BAAI · Downloadable

Gemma2-9B-IT-Simpo-Infinity-Preference

Text generation

Generates text, according to its published model architecture (Gemma2ForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Source listed
Aug 28, 2024
Parameters
9B
4-bit weights only
≈ 4.5 GB
License
Not disclosed
Compare this model →

inclusionAI · Downloadable

UI-Venus-2-9B

Vision

Understands text and images and responds in text.

Source listed
Aug 26, 2026
Parameters
9B
4-bit weights only
≈ 4.5 GB
License
Not disclosed
Compare this model →

inclusionAI · Downloadable

VISTA-9B

VisionReinforcement learning

Understands text and images and responds in text.

Source listed
Jun 12, 2026
Parameters
9B
4-bit weights only
≈ 4.5 GB
License
apache-2.0
Compare this model →

Microsoft · Downloadable

Fara1.5-9B

Vision

Understands text and images and responds in text.

Source listed
May 12, 2026
Parameters
9B
4-bit weights only
≈ 4.5 GB
License
mit
Compare this model →

Ornith · Downloadable

Ornith-1.0-9B

VisionCoding

Designed for coding and software tasks. Understands text and images and responds in text.

Source listed
Jun 21, 2026
Parameters
9B
4-bit weights only
≈ 4.5 GB
License
mit
Compare this model →

Ornith · Downloadable

Ornith-1.5-9B

VisionCoding

Built for coding agents and multi-step tasks. An open-weight model from the Ornith team.

Source listed
Aug 18, 2026
Parameters
9B
4-bit weights only
≈ 4.5 GB
License
mit
Compare this model →

What changes with a 16GB budget?

With 2 GB set aside, 14 GB remains for weights. At 4-bit that allows up to 28 billion parameters in the theoretical calculation. An 8-billion-parameter model alone needs approximately 4 GB at this precision, before its conversation cache and runtime.

Why might a listed model still fail to load?

Its actual weight format may need more space, the runtime may not support its architecture, or the conversation cache may exceed your reserve. Vision models can also need space for image processing. Check the original model card and measure your exact setup before relying on it.

Read the memory guide and technical sources · Compare two models