Best local AI models for AMD RX 470
4 GB GDDR5. At a 4k context, 81 of the 233 models in our catalog with verified parameter counts fit fully, up to Lumina-Next / Lumina-Image 2.0 at 5B parameters.
Check your own machine against every model →The largest models that fit fully
The 30 largest of the 81 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.
| Model | Parameters | Best quant that fits | Memory used at 4k |
|---|---|---|---|
| Lumina-Next / Lumina-Image 2.0 | 5B | Q4_K_M | 3.7 GB |
| CogVideoX 2B / 5B | 5B | Q4_K_M | 3.7 GB |
| DeepSeek-VL2 | 4.5B | Q5_K_M | 3.8 GB |
| DeepFloyd IF | 4.3B | Q5_K_M | 3.7 GB |
| Phi-3.5-vision | 4.2B | Q5_K_M | 3.6 GB |
| Qwen3 4B | 4B | Q6_K | 3.9 GB |
| Gemma 3 4B | 4B | Q6_K | 3.9 GB |
| Gemma 4 E4B | 4B | Q6_K | 3.9 GB |
| MiniCPM 3 4B | 4B | Q6_K | 3.9 GB |
| Danube 3 4B | 4B | Q6_K | 3.9 GB |
| Fish Speech 1.5 / OpenAudio S1 | 4B | Q6_K | 3.9 GB |
| Phi-4-mini-instruct | 3.8B | Q6_K | 3.7 GB |
| Phi-3.5 Mini | 3.8B | Q6_K | 3.7 GB |
| OmniGen / OmniGen2 | 3.8B | Q6_K | 3.7 GB |
| SD Cascade (Würstchen v3) | 3.6B | Q6_K | 3.5 GB |
| SDXL Turbo | 3.5B | Q6_K | 3.4 GB |
| SDXL Lightning | 3.5B | Q6_K | 3.4 GB |
| ACE-Step | 3.5B | Q6_K | 3.4 GB |
| MusicGen small/medium/large | 3.3B | Q6_K | 3.2 GB |
| SmolLM3 3B | 3B | Q8_0 | 3.8 GB |
| Replit Code v1.5 3B | 3B | Q8_0 | 3.8 GB |
| Kandinsky 3.1 | 3B | Q8_0 | 3.8 GB |
| Voxtral Mini / Small | 3B | Q8_0 | 3.8 GB |
| Orpheus TTS | 3B | Q8_0 | 3.8 GB |
| Higgs Audio v2 | 3B | Q8_0 | 3.8 GB |
| Allegro | 2.8B | Q8_0 | 3.6 GB |
| Open-Sora Plan | 2.7B | Q8_0 | 3.4 GB |
| LFM2 1.2B / 2.6B | 2.6B | Q8_0 | 3.3 GB |
| Playground v2.5 | 2.6B | Q8_0 | 3.3 GB |
| Stable Diffusion 3.5 Medium | 2.5B | Q8_0 | 3.2 GB |
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.
| Model | Parameters | Memory at FP8 / optimized | System RAM at 4k |
|---|---|---|---|
| Stable Diffusion XL | 3.417B | 4.1 GB needed | 6.1 GB |
| Phi-3 Mini | 3.8B | 4.4 GB needed | 6.4 GB |
| Phi-4-multimodal | 5.6B | 4.1 GB needed | 6.1 GB |
| Magicoder-S-DS 6.7B | 6.7B | 4.9 GB needed | 6.9 GB |
| Mistral 7B | 7B | 5.7 GB needed | 7.7 GB |
| Qwen2.5 0.5B / 1.5B / 3B / 7B | 7B | 5.1 GB needed | 7.1 GB |
| OLMo 2 1B / 7B | 7B | 5.1 GB needed | 7.1 GB |
| Falcon 3 1B / 3B / 7B | 7B | 5.1 GB needed | 7.1 GB |
| Command R7B | 7B | 5.1 GB needed | 7.1 GB |
| OpenHermes 2.5 | 7B | 5.1 GB needed | 7.1 GB |
How to read this
The AMD RX 470 graphics card features 4 GB of GDDR5 video memory. This memory size determines which artificial intelligence models can run directly on your hardware. To run a model entirely on the graphics card, the model files and active memory must fit within this 4 GB limit. If a model exceeds this capacity, your system will slow down or fail to run the model.
Quantization is a method that compresses model files to save space. In our tables, the best quant column shows the highest quality compression level that safely fits within the 4 GB limit of your card. For example, a Q6_K quant uses less space than a Q8_0 quant. This compression allows you to run larger and more capable models than would otherwise be possible on this hardware.
Several models can fit completely within your video memory. The largest options include Lumina-Next or Lumina-Image 2.0 at 5B using a Q4_K_M quant which takes 3.7 GB of space. You can also run CogVideoX 2B or 5B at 5B using a Q4_K_M quant for 3.7 GB. DeepSeek-VL2 at 4.5B fits with a Q5_K_M quant using 3.8 GB. Other options include DeepFloyd IF at 4.3B using 3.7 GB and Phi-3.5-vision at 4.2B using 3.6 GB.
For text and generation models, you can run Qwen3 4B, Gemma 3 4B, Gemma 4 E4B, MiniCPM 3 4B, Danube 3 4B, and Fish Speech 1.5 or OpenAudio S1 at 4B. These models use a Q6_K quant and require 3.9 GB of memory. Phi-4-mini-instruct, Phi-3.5 Mini, and OmniGen or OmniGen2 at 3.8B use a Q6_K quant and require 3.7 GB. You can also run SD Cascade (Würstchen v3) at 3.6B using 3.5 GB, or SDXL Turbo and SDXL Lightning at 3.5B using 3.4 GB.
If you want to run larger models, you must use CPU offload. This process splits the model between your graphics card and your system RAM. We assume you have 32 GB of system RAM for these cases. Offloading allows you to run Mistral 7B, Qwen2.5 0.5B / 1.5B / 3B / 7B, OLMo 2 1B / 7B, Falcon 3 1B / 3B / 7B, Command R7B, or OpenHermes 2.5. These 7B models require 5.1 GB of video memory at Q4_K_M and 7.1 GB of system RAM.
Other offload options include Magicoder-S-DS 6.7B which needs 4.9 GB at Q4_K_M and 6.9 GB of system RAM. Phi-4-multimodal at 5.6B needs 4.1 GB at Q4_K_M and 6.1 GB of system RAM. Stable Diffusion XL at 3.417B needs 4.1 GB at FP8 or optimized settings and 6.1 GB of system RAM. Phi-3 Mini at 3.8B needs 4.4 GB at Q4_K_M and 6.4 GB of system RAM. Offloading makes these models work but it reduces your generation speed.
You must also consider the context window when running these models. The memory figures listed here are calculated using a basic 4k context window. If you increase the context length to process longer documents or chat histories, the model will require significantly more video memory. This extra memory usage can easily push a model past the 4 GB limit of your card.