Best local AI models for AMD RX 7800 XT

The largest models that fit fully

The 30 largest of the 155 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 RX 7800 XT graphics card features 16 GB of GDDR6 memory. This physical memory size determines the maximum size of the artificial intelligence models you can run locally. To run a model entirely on the graphics hardware, the model files and the active context data must fit within this 16 GB limit.

The quantization column shows the compression level used for each model. Quantization reduces the size of model weights to save memory. For example, the Q4_K_M quant represents a four bit compression level. The Q6_K and Q8_0 quants offer higher precision but require more memory. Choosing the best quant allows you to balance output quality and memory usage.

Several large models fit completely inside the 16 GB memory of the RX 7800 XT. The gpt-oss-20b and Reka Flash 3 models use 15.4 GB of memory at the Q4_K_M quant. The Qwen-Image and Qwen-Image-Edit models use 14.6 GB of memory at the same quant. CogVLM2 uses 13.9 GB at Q4_K_M. HunyuanImage 2.1 / 3.0 uses 14.5 GB at the Q5_K_M quant, while Ling-Coder-Lite uses 14.3 GB at Q5_K_M.

You can also run high precision models at Q6_K and Q8_0 quants. DeepSeek-Coder-V2 16B / 236B and Kimi-VL A3B both use 15.7 GB at Q6_K. Apriel-1.5-15B-Thinker and StarCoder2 3B / 7B / 15B use 14.8 GB at Q6_K. Qwen2.5 14B uses 15.3 GB at Q6_K. Phi-4 and Phi-4-reasoning / -plus use 13.8 GB at Q6_K. Gemma 4 12B and Mistral NeMo 12B use 15.3 GB at the Q8_0 quant.

When a model exceeds 16 GB, you must offload parts of it to your system RAM. This offloading process slows down processing speeds significantly. For offloading, we assume a system with 32 GB of system RAM. Solar Pro and Codestral 22B require 16.1 GB of memory at Q4_K_M and need 18.1 GB of system RAM. Mistral Small 3.2 and Magistral Small require 17.6 GB at Q4_K_M and need 19.6 GB of system RAM.

Larger offloaded models require even more system RAM. Aria requires 18.3 GB at Q4_K_M and needs 20.3 GB of system RAM. Gemma 4 26B-A4B requires 19 GB at Q4_K_M and needs 21 GB of system RAM. Gemma 3 27B requires 19.8 GB at Q4_K_M and needs 21.8 GB of system RAM.

All memory calculations in our catalog assume a standard 4k context window. If you increase the context window to process longer texts, the model will require more memory. Running a model very close to the 16 GB limit of your RX 7800 XT may cause out of memory errors if your context window grows too large.