Best local AI models for AMD R7 M270

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 M270 is an entry level graphics card equipped with 2 GB of DDR3 video memory. This specific VRAM capacity determines the size of the artificial intelligence models you can run locally on your hardware. Because DDR3 memory has lower bandwidth than modern graphics memory, choosing the correct model size and quantization level is critical to achieve acceptable generation speeds.

The quantization column indicates the compression level applied to each model. Quantization reduces the precision of model weights to save memory. For example, the Allegro 2.8B model fits in 2 GB of VRAM when using the Q4_K_M quantization. Smaller models like the SmolLM2 1.7B can run at the higher quality Q6_K quantization while using 1.7 GB of VRAM. Tiny models like the TinyLlama 1.1B can run at the maximum Q8_0 quantization using only 1.4 GB of VRAM.

When a model exceeds the 2 GB VRAM limit of your AMD R7 M270, 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. For instance, running the SmolLM3 3B model at Q4_K_M requires 2.2 GB of memory, which uses your full VRAM and offloads 4.2 GB to your system RAM. Running Stable Diffusion XL requires 4.1 GB of memory at FP8, which offloads 6.1 GB to your system RAM.

CPU offload allows you to run larger architectures like the 3.5B SDXL Turbo or SDXL Lightning. However, offloading introduces a significant performance cost. System RAM is much slower than video memory, and transferring data between the CPU and GPU creates a bottleneck. While offloading makes it possible to run these larger models, your generation times will be much longer compared to models that fit entirely within your 2 GB video memory.

You must also consider the memory cost of context length when running text models. The memory figures listed for models like Canary 1B or Qwen-2.5B assume a minimal context window. If you increase the context window to 4k tokens, the key value cache will require additional memory. This extra memory consumption can easily push a model over the 2 GB limit, forcing unexpected CPU offload and slowing down your generation speeds.