Best local AI models for AMD R9 380X

4 GB GDDR5. At a 4k context, 81 of the 233 models in our catalog with verified parameter counts fit fully, up to Lumina-Next / Lumina-Image 2.0 at 5B parameters.

Check your own machine against every model →

The largest models that fit fully

The 30 largest of the 81 models that fit; every smaller model in the catalog fits too. Best quant means the highest quality compression whose weights and 4k context both sit inside the memory.

ModelParametersBest quant that fitsMemory used at 4k
Lumina-Next / Lumina-Image 2.05BQ4_K_M3.7 GB
CogVideoX 2B / 5B5BQ4_K_M3.7 GB
DeepSeek-VL24.5BQ5_K_M3.8 GB
DeepFloyd IF4.3BQ5_K_M3.7 GB
Phi-3.5-vision4.2BQ5_K_M3.6 GB
Qwen3 4B4BQ6_K3.9 GB
Gemma 3 4B4BQ6_K3.9 GB
Gemma 4 E4B4BQ6_K3.9 GB
MiniCPM 3 4B4BQ6_K3.9 GB
Danube 3 4B4BQ6_K3.9 GB
Fish Speech 1.5 / OpenAudio S14BQ6_K3.9 GB
Phi-4-mini-instruct3.8BQ6_K3.7 GB
Phi-3.5 Mini3.8BQ6_K3.7 GB
OmniGen / OmniGen23.8BQ6_K3.7 GB
SD Cascade (Würstchen v3)3.6BQ6_K3.5 GB
SDXL Turbo3.5BQ6_K3.4 GB
SDXL Lightning3.5BQ6_K3.4 GB
ACE-Step3.5BQ6_K3.4 GB
MusicGen small/medium/large3.3BQ6_K3.2 GB
SmolLM3 3B3BQ8_03.8 GB
Replit Code v1.5 3B3BQ8_03.8 GB
Kandinsky 3.13BQ8_03.8 GB
Voxtral Mini / Small3BQ8_03.8 GB
Orpheus TTS3BQ8_03.8 GB
Higgs Audio v23BQ8_03.8 GB
Allegro2.8BQ8_03.6 GB
Open-Sora Plan2.7BQ8_03.4 GB
LFM2 1.2B / 2.6B2.6BQ8_03.3 GB
Playground v2.52.6BQ8_03.3 GB
Stable Diffusion 3.5 Medium2.5BQ8_03.2 GB

Close, but only with CPU offload

These need more than the card holds at their smallest practical quant, so part of the model runs from system memory (figures assume 32 GB of it). They work, several times slower.

ModelParametersMemory at FP8 / optimizedSystem RAM at 4k
Stable Diffusion XL3.417B4.1 GB needed6.1 GB
Phi-3 Mini3.8B4.4 GB needed6.4 GB
Phi-4-multimodal5.6B4.1 GB needed6.1 GB
Magicoder-S-DS 6.7B6.7B4.9 GB needed6.9 GB
Mistral 7B7B5.7 GB needed7.7 GB
Qwen2.5 0.5B / 1.5B / 3B / 7B7B5.1 GB needed7.1 GB
OLMo 2 1B / 7B7B5.1 GB needed7.1 GB
Falcon 3 1B / 3B / 7B7B5.1 GB needed7.1 GB
Command R7B7B5.1 GB needed7.1 GB
OpenHermes 2.57B5.1 GB needed7.1 GB

How to read this

The AMD Radeon R9 380X graphics card features 4 GB of GDDR5 video memory. This memory size determines which artificial intelligence models can run entirely on your hardware. When a model fits inside your video memory, it runs at maximum speed. If a model exceeds this limit, you must use system memory offloading which slows down generation speeds.

The quantization column shows the compression level used to fit these models into memory. Quantization reduces the precision of model weights to save space. For example, a Q4_K_M quant uses four bit quantization to compress models like Lumina-Next or CogVideoX 5B down to 3.7 GB. A Q6_K quant offers higher precision for 4B models like Gemma 3 4B and Qwen3 4B. The Q8_0 quant provides the highest quality and fits 3B models like SmolLM3 3B and Kandinsky 3.1 within 3.8 GB.

To run larger models, you can offload a portion of the workload to your system RAM. This approach assumes your computer has 32 GB of system RAM. Offloading allows you to run Mistral 7B or Falcon 3 7B which require 5.1 GB to 5.7 GB of memory at Q4_K_M. This method also lets you run Stable Diffusion XL at FP8 which needs 4.1 GB of video memory and 6.1 GB of system RAM.

When running models on a 4 GB card, you must monitor your context window size. The standard four thousand token context window requires additional video memory during active generation. Running a model near the 4 GB limit can cause out of memory errors if your text prompt or history grows too large. Keeping your context short helps maintain stable performance.

For image and video generation, several options fit within the local memory limit. You can run SDXL Turbo and SDXL Lightning at Q6_K using 3.4 GB of video memory. Stable Diffusion 3.5 Medium fits at Q8_0 using 3.2 GB of video memory. For audio tasks, Orpheus TTS and Higgs Audio v2 run at Q8_0 using 3.8 GB of video memory.