Best local AI models for AMD R5 M255

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 Radeon R5 M255 is an entry level laptop graphics card equipped with 2 GB of DDR3 video memory. This dedicated memory size determines which artificial intelligence models can run directly on your hardware. Because DDR3 memory has lower bandwidth than modern graphics memory, keeping the entire model inside the 2 GB limit is crucial for maintaining usable processing speeds.

To fit inside this 2 GB limit, models use quantization. The quant column indicates the compression level applied to the model weights. For example, the Allegro 2.8B model fits in 2 GB of video memory when using the Q4_K_M quantization level. Smaller models like the SmolLM2 1.7B can run at a higher quality Q6_K quantization while using 1.7 GB of video memory. The TinyLlama 1.1B model fits easily at the high quality Q8_0 quantization level while using only 1.4 GB of video memory.

When a model exceeds the 2 GB video memory limit, you must use CPU offload. This technique splits the workload between your graphics card and your system RAM. If you have 32 GB of system RAM, you can run larger models like the SmolLM3 3B or the Replit Code v1.5 3B. These models need 2.2 GB of video memory at Q4_K_M quantization and require an additional 4.2 GB of system RAM to function.

CPU offload allows you to run advanced image generation models like Stable Diffusion XL. This model has 3.417B parameters and needs 4.1 GB at FP8 or optimized settings, which requires 6.1 GB of system RAM. However, transferring data between DDR3 video memory and system RAM over the system bus creates a performance cost. Offloading will significantly slow down the generation speed compared to models that fit entirely within the local 2 GB video memory.

You must also consider the memory cost of context length. Running a text model with a standard 4k context window requires extra video memory to store the active conversation history. If a model like the Canary 1B or Qwen-2.5B uses 1.8 GB of video memory at Q4_K_M, there is very little space left for this context. To prevent out of memory errors, you may need to reduce the context length or choose a smaller model like the SantaCoder 1.1B.