Best local AI models for AMD HD 8690M

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 HD 8690M is a mobile graphics card equipped with 2 GB GDDR5 memory. This dedicated video memory determines the maximum size of the artificial intelligence models you can run entirely on the hardware. To fit models within this limit, developers use quantization. Quantization reduces the precision of model weights to save space. The quant column shows the best balance of size and quality for each model.

For models up to 2.8B parameters, you can run execution entirely inside the 2 GB video memory. The Allegro 2.8B model fits using the Q4_K_M quant which uses exactly 2 GB. Open-Sora Plan 2.7B also fits at Q4_K_M using 2 GB. Smaller models like LFM2 2.6B and Playground v2.5 2.6B require 1.9 GB at Q4_K_M. Stable Diffusion 3.5 Medium 2.5B and Canary 2.5B fit using 1.8 GB at the same quantization level.

As model sizes decrease, you can use higher quality quantization levels. SeamlessM4T v2 2.3B, Parler-TTS 2.2B, and Kimi K3 DSpark 2.2B run well using the Q5_K_M quant. Models like SmolVLM 2B, Stable Diffusion 3 Medium 2B, Pyramid Flow 2B, and Wav2Vec2 2B utilize the Q6_K quant and use 2 GB of memory. Moondream 2 1.9B fits at Q6_K using 1.9 GB. Qwen3 1.7B and SmolLM2 1.7B use 1.7 GB at Q6_K.

Very small models can run at the highest quality Q8_0 quantization level. StableLM 2 1.6B, Sana 1.6B, Zonos 0.1 1.6B, and Dia 1.6B all use 2 GB at Q8_0. Whisper Large v3 1.55B uses 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 all require 1.9 GB at Q8_0. Tango 2 1.4B uses 1.8 GB, while TinyLlama 1.1B and SantaCoder 1.1B use 1.4 GB at Q8_0.

When a model exceeds the 2 GB video memory, you must offload parts of it to your system RAM. This offload process allows you to run larger models but slows down processing speed. For these cases, we assume your system has 32 GB system RAM. SmolLM3 3B, Replit Code v1.5 3B, Kandinsky 3.1 3B, Voxtral 3B, Orpheus TTS 3B, and Higgs Audio v2 3B need 2.2 GB of video memory at Q4_K_M and 4.2 GB of system RAM.

Larger offload models require even more system RAM. MusicGen 3.3B needs 2.4 GB of video memory 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 both need 2.6 GB of video memory at Q4_K_M and 4.6 GB of system RAM. Note that running models at a standard 4k context window increases memory usage beyond these base requirements.