Best local AI models for AMD R9 390

The largest models that fit fully

The 30 largest of the 123 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.

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.

How to read this

The AMD Radeon R9 390 graphics card features 8 GB of GDDR5 onboard memory. This memory size determines which artificial intelligence models can run directly on your hardware. For local execution, the model weights must fit inside this video memory to run at full speed. If a model exceeds this limit, your system must use system memory, which slows down processing speeds.

Quantization is a method that compresses model files to save space. The quant column shows the best balance of size and quality for each model. For example, Gemma 2 9B fits at the Q4_K_M quantization level, which uses exactly 8 GB of video memory. Smaller models like Llama 3.1 8B can run at the higher quality Q5_K_M quantization level while using 7.4 GB of video memory.

Many high quality models fit completely within your video memory. Mochi 1 10B runs at Q4_K_M using 7.3 GB of memory. You can run Granite 3.3 8B, Ministral 8B, InternLM 3 8B, OpenCoder 8B, Seed-Coder 8B, MiniCPM-V 2.6, Idefics 3 8B, Fuyu-8B, Emu3, and Stable Diffusion 3.5 Large at the Q6_K quantization level using 7.9 GB of memory. Other options like Nemotron Nano 9B, GLM-4 9B, Yi-Coder 9B, GLM-4-9B-Chat, and GLM-4V-9B fit at Q5_K_M using 7.7 GB of memory. Chroma 8.9B fits at Q5_K_M using 7.6 GB of memory.

You can also run 7B models with excellent precision. Mistral 7B uses 7.4 GB of memory at the Q6_K quantization level. Qwen2.5 7B, OLMo 2 7B, Falcon 3 7B, Command R7B, OpenHermes 2.5, Zephyr 7B Beta, OpenChat 3.5, Starling LM 7B, and Codestral Mamba 7B all use 6.9 GB of memory at the Q6_K quantization level. EXAONE 3.5 7.8B uses 7.7 GB of memory at the Q6_K quantization level.

When a model is too large for the video memory, you must offload parts of it to your system RAM. This offload process allows you to run larger models but reduces performance. For these cases, we assume your computer has 32 GB of system RAM. Open-Sora 2.0 11B needs 8.1 GB at Q4_K_M and requires 10.1 GB of system RAM. Gemma 3 12B, Gemma 4 12B, Mistral NeMo 12B, Pixtral 12B, FLUX.1 schnell, FLUX.1 Kontext dev, and FLUX.1 Krea dev need 8.8 GB at Q4_K_M and require 10.8 GB of system RAM. FLUX.1 dev 12B needs 14.4 GB at FP8 and requires 16.4 GB of system RAM. Vicuna 13B needs 9.5 GB at Q4_K_M and requires 11.5 GB of system RAM.

Memory calculations are based on a standard 4k context window. If you increase the context window to process longer documents, the model will require more video memory. Running a model close to the 8 GB limit of your AMD R9 390 might cause out of memory errors if the context window grows too large.