Best local AI models for AMD R7 M360

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 R7 M360 is an entry level laptop graphics card equipped with 2 GB of DDR3 video memory. This dedicated memory pool is the primary constraint when running local artificial intelligence models. To run a model entirely on this hardware without performance penalties the total memory footprint must fit within this 2 GB limit. When a model exceeds this capacity the system must offload parts of the workload to system RAM which reduces processing speeds.

The quantization column indicates the compression level applied to each model. Quantization reduces the precision of model weights to save space. For example a Q4_K_M quantization represents a four bit format that balances size and output quality. Higher quantizations like Q6_K or Q8_0 offer better accuracy but require more memory. Choosing the correct quantization is essential to fit larger models like the 2.8B Allegro or the 2.7B Open-Sora Plan into the limited 2 GB video memory.

Several capable models can run fully within the local video memory. The 2.6B LFM2 and 2.6B Playground v2.5 models fit well at Q4_K_M quantization using 1.9 GB of memory. Image generation models such as Stable Diffusion 3.5 Medium fit at Q4_K_M using 1.8 GB of memory. Smaller models like the 1.7B Qwen3 and 1.7B SmolLM2 can run at a higher Q6_K quantization while using 1.7 GB of video memory. For maximum precision the 1.1B TinyLlama and 1.1B SantaCoder can run at Q8_0 quantization using 1.4 GB of memory.

When models exceed the 2 GB video memory limit you must use CPU offloading. This process splits the model layers between your graphics card and your system RAM. For these scenarios we assume your computer has 32 GB of system RAM. Running the 3B SmolLM3 or the 3B Replit Code v1.5 at Q4_K_M requires 2.2 GB of video memory and 4.2 GB of system RAM. Similarly the 3.5B SDXL Turbo requires 2.6 GB of video memory and 4.6 GB of system RAM to operate.

Offloading comes with a significant performance cost. DDR3 video memory is already slower than modern GDDR standards and transferring data between the graphics card and system RAM creates a bottleneck. While offloading allows you to run larger models like the 3.417B Stable Diffusion XL or the 3.3B MusicGen it will result in much slower generation times compared to models that fit entirely within the 2 GB video memory.

Users must also consider the memory cost of context windows. Running text models with a standard 4k context window requires additional memory beyond the base model size. This context overhead can easily push a model that normally fits in 1.9 GB over the strict 2 GB hardware limit. To avoid running out of memory you may need to reduce the context length or select a smaller model like the 1.6B Dia or the 1.5B Hunyuan-DiT.