Best local AI models for AMD HD 7690M XT

The largest models that fit fully

The 30 largest of the 56 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 HD 7690M XT is a legacy mobile graphics card equipped with 2 GB of GDDR5 memory. This dedicated video memory determines the maximum size of the artificial intelligence models you can run entirely on the hardware. When a model fits completely within this 2 GB limit, it executes with the fastest possible processing speeds. If a model exceeds this capacity, it cannot run solely on the graphics hardware.

To fit larger models into the limited memory, quantization is used to compress the files. The quantization column shows the best format that balances model accuracy and memory limits. For example, Allegro 2.8B and Open-Sora Plan 2.7B both use the Q4_K_M quantization to fit exactly into 2 GB of video memory. Smaller models like SmolLM2 1.7B can run at a higher quality Q6_K quantization while using 1.7 GB of memory. TinyLlama 1.1B runs at the highly accurate Q8_0 quantization using only 1.4 GB of memory.

When you want to run models that are larger than 2 GB, you must use CPU offloading. This technique splits the workload between your graphics card and your system memory. Assuming your computer has 32 GB of system RAM, you can run models like the 3B parameter SmolLM3 or Replit Code v1.5. These models require 2.2 GB of video memory at Q4_K_M quantization and an additional 4.2 GB of system RAM. You can also run Stable Diffusion XL, which requires 4.1 GB of video memory at FP8 and 6.1 GB of system RAM.

CPU offloading allows you to run advanced tools like SDXL Turbo or SDXL Lightning. These 3.5B parameter models need 2.6 GB of video memory at Q4_K_M quantization and 4.6 GB of system RAM. However, offloading comes with a performance cost. Moving data between the graphics card and system RAM is much slower than keeping everything in the dedicated GDDR5 memory. Your processing speeds will drop significantly when offloading is active.

You must also consider the memory cost of context length. The memory figures listed for these models assume a standard 4k context window. If you increase the context window to process longer documents or conversations, the system will require more memory. This extra memory usage can easily push a model over the 2 GB limit of your AMD HD 7690M XT, forcing the system to use slower CPU offloading even for smaller models.