Best local AI models for AMD R7 370

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 R7 370 graphics card features 2 GB of GDDR5 video memory. This memory capacity determines which local AI models can run directly on the hardware. To fit within this limit, models must be compressed using quantization. The quantization column shows the best format that balances model accuracy and memory usage for your card.

For models that fit entirely in video memory, the Allegro 2.8B model is the largest option at a Q4_K_M quantization using 2 GB. Other options include Open-Sora Plan 2.7B at Q4_K_M using 2 GB and LFM2 2.6B at Q4_K_M using 1.9 GB. Playground v2.5 2.6B also runs at Q4_K_M using 1.9 GB. Stable Diffusion 3.5 Medium 2.5B and Canary 2.5B both use 1.8 GB with Q4_K_M quantization.

Higher quantization levels like Q5_K_M and Q6_K offer better quality for slightly smaller models. SeamlessM4T v2 2.3B and Kimi K3 DSpark 2.2B both use 2 GB at Q5_K_M quantization. Parler-TTS 2.2B uses 1.9 GB at Q5_K_M. SmolVLM 2B, Stable Diffusion 3 Medium 2B, Pyramid Flow 2B, and Wav2Vec2 XLS-R 2B all run at Q6_K quantization using 2 GB. Moondream 2 1.9B uses 1.9 GB at Q6_K, while Qwen3 1.7B and SmolLM2 1.7B use 1.7 GB at Q6_K.

Small models can run at Q8_0 quantization for maximum precision. StableLM 2 1.6B, Sana 1.6B, Zonos 0.1 1.6B, Dia 1.6B, and Whisper Large v3 1.55B all use 2 GB at Q8_0. ControlNet 1.5B, Hunyuan-DiT 1.5B, Stable Video Diffusion 1.5B, Whisper Large v2 1.5B, AudioGen 1.5B, and AudioLDM 2 1.5B use 1.9 GB at Q8_0. Tango 2 1.4B uses 1.8 GB at Q8_0, while TinyLlama 1.1B and SantaCoder 1.1B use 1.4 GB at Q8_0.

When a model exceeds the 2 GB video memory limit, you can use CPU offload if your system has 32 GB of system RAM. Offloading splits the model between your graphics card and system memory. This process allows you to run larger models, but it reduces generation speed because system RAM is slower than GDDR5 video memory.

With CPU offload, you can run SmolLM3 3B, Replit Code v1.5 3B, Kandinsky 3.1 3B, Voxtral 3B, Orpheus TTS 3B, and Higgs Audio v2 3B. These models need 2.2 GB at Q4_K_M and 4.2 GB of system RAM. MusicGen 3.3B needs 2.4 GB at Q4_K_M and 4.4 GB of system RAM. Stable Diffusion XL 3.417B needs 4.1 GB at FP8 and 6.1 GB of system RAM. SDXL Turbo 3.5B and SDXL Lightning 3.5B need 2.6 GB at Q4_K_M and 4.6 GB of system RAM.

Memory calculations assume a standard 4k context window. Increasing the context window length will require more video memory for temporary data. If you experience out of memory errors during long generations, you must reduce the context length or use a smaller model.