Best local AI models for AMD R9 M380

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.

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 M380 is an older graphics card equipped with 4 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 4 GB limit, the graphics processor handles all calculations. This local execution ensures the fastest possible generation speeds for text, images, and audio without relying on external cloud servers.

To fit modern models into this memory limit, developers use quantization. Quantization is a compression method represented by the quant column, which reduces the precision of model weights. For example, a Q4_K_M quant uses approximately four bits per weight, while Q6_K and Q8_0 quants offer higher precision at the cost of larger file sizes. On this hardware, models like Lumina-Next or CogVideoX 2B / 5B can run at Q4_K_M using 3.7 GB of memory. Smaller architectures like SmolLM3 3B or Kandinsky 3.1 can run at higher quality Q8_0 quants using 3.8 GB of memory.

If a model exceeds the 4 GB video memory limit, you must use CPU offload. This technique splits the model weights between your graphics card and your system RAM. We assume your computer has 32 GB of system RAM for these scenarios. Offloading allows you to run larger architectures, but it introduces a significant performance cost. Because system RAM is much slower than GDDR5 video memory, transfer bottlenecks will slow down your generation speeds.

With CPU offload active, you can run larger models such as Mistral 7B, which requires 5.7 GB at Q4_K_M and 7.7 GB of system RAM. Other options include Qwen2.5 7B, OLMo 2 7B, Falcon 3 7B, Command R7B, and OpenHermes 2.5, which all require 5.1 GB at Q4_K_M and 7.1 GB of system RAM. You can also run specialized tools like Magicoder-S-DS 6.7B, which needs 4.9 GB at Q4_K_M and 6.9 GB of system RAM, or Phi-4-multimodal, which needs 4.1 GB at Q4_K_M and 6.1 GB of system RAM.

You must also consider the context window when planning your memory allocation. The memory figures listed for these models assume a standard base context of 4k tokens. As your conversation grows longer, the active memory required to track the history increases. Running close to the 4 GB limit of your AMD R9 M380 means that long conversations or large prompts might exceed your remaining video memory and trigger unexpected slowdowns.