YOUR MEMORY BUDGET

Local AI models for 8GB VRAM.

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

6 GBleft for weights at 4-bit
8 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.

852 models within the weight budget

Largest parameter count first · not a quality ranking

OpenBMB · Downloadable

NOSA-8B

Text generation

Generates text for conversations and writing.

Source listed
Jan 4, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

OpenMOSS · Downloadable

Qwen3-8B-ABC

Text generation

Generates text for conversations and writing.

Source listed
Jan 14, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

OpenMOSS · Downloadable

Qwen3-8B-base-mla-topk8-rank1024

Text generation

Generates text, according to its published model architecture (Qwen3ForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Source listed
Aug 28, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

OpenMOSS · Downloadable

Qwen3-8B-base-mla-topk8-rank256

Text generation

Generates text, according to its published model architecture (Qwen3ForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Source listed
Aug 28, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

OpenMOSS · Downloadable

Qwen3-8B-base-mla-topk8-rank512

Text generation

Generates text, according to its published model architecture (Qwen3ForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Source listed
Aug 28, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

PrismML · Downloadable

Bonsai-8B

Text generation

Generates text for conversations and writing.

Source listed
Mar 18, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

Qwen · Alibaba · Downloadable

Qwen3-8B

Text generation

Generates text for conversations and writing.

Source listed
Apr 27, 2025
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

Qwen · Alibaba · Downloadable

Qwen3-VL-8B-Thinking

VisionReasoning

Understands text and images and responds in text. Supports a reasoning mode.

Source listed
Oct 11, 2025
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

Qwen · Alibaba · Downloadable

WebWorld-8B

Text generation

Generates text for conversations and writing.

Source listed
Feb 13, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

StepFun · Downloadable

PaCoRe-8B

Text generation

Generates text for conversations and writing.

Source listed
Dec 9, 2025
Parameters
8B
4-bit weights only
≈ 4 GB
License
mit
Compare this model →

StepFun · Downloadable

RLVR-8B-0926

Text generation

Generates text for conversations and writing.

Source listed
Dec 9, 2025
Parameters
8B
4-bit weights only
≈ 4 GB
License
mit
Compare this model →

Tencent · Downloadable

Penguin-VL-8B

Text generation

Generates text for conversations and writing.

Source listed
Mar 5, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
apache-2.0
Compare this model →

Tencent · Downloadable

Sequential-Hidden-Decoding-8B-n2

Text generationCoding

Generates text, according to its published model architecture (Qwen3ScaleSeqForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Source listed
Mar 10, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
other
Compare this model →

Tencent · Downloadable

Sequential-Hidden-Decoding-8B-n4

Text generationCoding

Generates text, according to its published model architecture (Qwen3ScaleSeqForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Source listed
Mar 10, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
other
Compare this model →

Tencent · Downloadable

Sequential-Hidden-Decoding-8B-n8

Text generationCoding

Generates text, according to its published model architecture (Qwen3ScaleSeqForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Source listed
Mar 10, 2026
Parameters
8B
4-bit weights only
≈ 4 GB
License
other
Compare this model →

What changes with a 8GB budget?

With 2 GB set aside, 6 GB remains for weights. At 4-bit that allows up to 12 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