Best local AI models for AMD R9 M390X
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 R9 M390X graphics card has 4 GB of GDDR5 memory. This memory size determines which local AI models can run directly on your hardware. To fit inside this limit, models must use quantization. Quantization is a compression method that reduces model size while keeping most of the original quality. The quant column shows the best compression level that fits within your video memory.
For models that fit entirely on the card, you can run up to 5B parameter sizes. Lumina-Next or Lumina-Image 2.0 and CogVideoX 2B or 5B both run at the 5B size using the Q4_K_M quant which uses 3.7 GB of memory. DeepSeek-VL2 at 4.5B fits using the Q5_K_M quant and uses 3.8 GB. DeepFloyd IF at 4.3B uses 3.7 GB with Q5_K_M. Phi-3.5-vision at 4.2B uses 3.6 GB with Q5_K_M.
Several 4B models fit using the Q6_K quant which uses 3.9 GB of memory. These models include Qwen3 4B, Gemma 3 4B, Gemma 4 E4B, MiniCPM 3 4B, Danube 3 4B, and Fish Speech 1.5 or OpenAudio S1. Phi-4-mini-instruct, Phi-3.5 Mini, and OmniGen or OmniGen2 at 3.8B also fit using Q6_K and use 3.7 GB of memory. Image generators like SD Cascade (Würstchen v3) at 3.6B use 3.5 GB, while SDXL Turbo and SDXL Lightning at 3.5B use 3.4 GB.
Smaller models can run at the higher quality Q8_0 quant. SmolLM3 3B, Replit Code v1.5 3B, Kandinsky 3.1, Voxtral Mini or Small, Orpheus TTS, and Higgs Audio v2 all use 3.8 GB of memory at Q8_0. Allegro at 2.8B uses 3.6 GB, Open-Sora Plan at 2.7B uses 3.4 GB, and LFM2 1.2B or 2.6B and Playground v2.5 at 2.6B use 3.3 GB. Stable Diffusion 3.5 Medium at 2.5B uses 3.2 GB with Q8_0.
When a model is too large for the 4 GB video memory, you can use CPU offload. This method splits the model between your graphics card and your system RAM. It allows you to run larger models but it reduces your processing speed. For these cases, we assume your computer has 32 GB of system RAM to handle the shared workload.
Using CPU offload, you can run Stable Diffusion XL at 3.417B which 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. Phi-4-multimodal at 5.6B needs 4.1 GB at Q4_K_M and 6.1 GB of system RAM. Magicoder-S-DS 6.7B needs 4.9 GB at Q4_K_M and 6.9 GB of system RAM.
You can also run 7B models with CPU offload. Mistral 7B needs 5.7 GB at Q4_K_M and 7.7 GB of system RAM. Qwen2.5 0.5B or 1.5B or 3B or 7B, OLMo 2 1B or 7B, Falcon 3 1B or 3B or 7B, Command R7B, and OpenHermes 2.5 all need 5.1 GB at Q4_K_M and 7.1 GB of system RAM. Note that memory usage calculations assume a standard 4k context window. Longer conversations will require more memory.