Best local AI models for AMD R9 280
3 GB GDDR5. At a 4k context, 76 of the 233 models in our catalog with verified parameter counts fit fully, up to Qwen3 4B at 4B parameters.
Check your own machine against every model →The largest models that fit fully
The 30 largest of the 76 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 |
|---|---|---|---|
| Qwen3 4B | 4B | Q4_K_M | 2.9 GB |
| Gemma 3 4B | 4B | Q4_K_M | 2.9 GB |
| Gemma 4 E4B | 4B | Q4_K_M | 2.9 GB |
| MiniCPM 3 4B | 4B | Q4_K_M | 2.9 GB |
| Danube 3 4B | 4B | Q4_K_M | 2.9 GB |
| Fish Speech 1.5 / OpenAudio S1 | 4B | Q4_K_M | 2.9 GB |
| Phi-4-mini-instruct | 3.8B | Q4_K_M | 2.8 GB |
| Phi-3.5 Mini | 3.8B | Q4_K_M | 2.8 GB |
| OmniGen / OmniGen2 | 3.8B | Q4_K_M | 2.8 GB |
| SD Cascade (Würstchen v3) | 3.6B | Q4_K_M | 2.6 GB |
| SDXL Turbo | 3.5B | Q5_K_M | 3 GB |
| SDXL Lightning | 3.5B | Q5_K_M | 3 GB |
| ACE-Step | 3.5B | Q5_K_M | 3 GB |
| MusicGen small/medium/large | 3.3B | Q5_K_M | 2.8 GB |
| SmolLM3 3B | 3B | Q6_K | 3 GB |
| Replit Code v1.5 3B | 3B | Q6_K | 3 GB |
| Kandinsky 3.1 | 3B | Q6_K | 3 GB |
| Voxtral Mini / Small | 3B | Q6_K | 3 GB |
| Orpheus TTS | 3B | Q6_K | 3 GB |
| Higgs Audio v2 | 3B | Q6_K | 3 GB |
| Allegro | 2.8B | Q6_K | 2.8 GB |
| Open-Sora Plan | 2.7B | Q6_K | 2.7 GB |
| LFM2 1.2B / 2.6B | 2.6B | Q6_K | 2.6 GB |
| Playground v2.5 | 2.6B | Q6_K | 2.6 GB |
| Stable Diffusion 3.5 Medium | 2.5B | Q6_K | 2.5 GB |
| Canary 1B / Qwen-2.5B | 2.5B | Q6_K | 2.5 GB |
| SeamlessM4T v2 | 2.3B | Q8_0 | 2.9 GB |
| Parler-TTS | 2.2B | Q8_0 | 2.8 GB |
| Kimi K3 DSpark | 2.2B | Q8_0 | 2.9 GB |
| SmolVLM 256M / 500M / 2B | 2B | Q8_0 | 2.5 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-3.5-vision | 4.2B | 3.1 GB needed | 5.1 GB |
| DeepFloyd IF | 4.3B | 3.1 GB needed | 5.1 GB |
| DeepSeek-VL2 | 4.5B | 3.3 GB needed | 5.3 GB |
| Lumina-Next / Lumina-Image 2.0 | 5B | 3.7 GB needed | 5.7 GB |
| CogVideoX 2B / 5B | 5B | 3.7 GB needed | 5.7 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 |
How to read this
The AMD R9 280 graphics card has 3 GB of GDDR5 memory. This memory size limits the size of the artificial intelligence models you can run directly on the hardware. To fit inside this memory space, models must use quantization. Quantization is a compression method that reduces the precision of model weights to save space.
The best quant column shows the highest quality compression level that still fits within your video memory. For example, Qwen3 4B, Gemma 3 4B, and Gemma 4 E4B can run at a Q4_K_M quantization level which uses 2.9 GB of memory. Other models like MiniCPM 3 4B, Danube 3 4B, and Fish Speech 1.5 / OpenAudio S1 also fit at Q4_K_M using 2.9 GB of memory. Models like Phi-4-mini-instruct, Phi-3.5 Mini, and OmniGen / OmniGen2 fit at Q4_K_M using 2.8 GB of memory.
Slightly smaller models can use higher quality quantization levels. SDXL Turbo, SDXL Lightning, and ACE-Step run at a Q5_K_M quantization level using 3 GB of memory. MusicGen small/medium/large fits at Q5_K_M using 2.8 GB of memory. Models like SmolLM3 3B, Replit Code v1.5 3B, Kandinsky 3.1, Voxtral Mini / Small, Orpheus TTS, and Higgs Audio v2 can run at a Q6_K quantization level using 3 GB of memory. Allegro fits at Q6_K using 2.8 GB of memory, while Open-Sora Plan fits at Q6_K using 2.7 GB of memory.
Very small models can run at the highest quantization levels. LFM2 1.2B / 2.6B and Playground v2.5 use Q6_K with 2.6 GB of memory. Stable Diffusion 3.5 Medium and Canary 1B / Qwen-2.5B use Q6_K with 2.5 GB of memory. SeamlessM4T v2 uses Q8_0 with 2.9 GB of memory. Parler-TTS uses Q8_0 with 2.8 GB of memory. Kimi K3 DSpark uses Q8_0 with 2.9 GB of memory. SmolVLM 256M / 500M / 2B uses Q8_0 with 2.5 GB of memory.
If a model is too large for your video memory, you must use CPU offload. This process splits the model between your graphics card and your system RAM. CPU offload allows you to run larger models, but it costs speed because system RAM is much slower than video memory. For these cases, we assume you have 32 GB of system RAM.
With CPU offload, you can run Stable Diffusion XL which needs 4.1 GB at FP8 / optimized and uses 6.1 GB of system RAM. You can run Phi-3 Mini which needs 4.4 GB at Q4_K_M and uses 6.4 GB of system RAM. Phi-3.5-vision and DeepFloyd IF need 3.1 GB at Q4_K_M and use 5.1 GB of system RAM. DeepSeek-VL2 needs 3.3 GB at Q4_K_M and uses 5.3 GB of system RAM. Lumina-Next / Lumina-Image 2.0 and CogVideoX 2B / 5B need 3.7 GB at Q4_K_M and use 5.7 GB of system RAM. Phi-4-multimodal needs 4.1 GB at Q4_K_M and uses 6.1 GB of system RAM. Magicoder-S-DS 6.7B needs 4.9 GB at Q4_K_M and uses 6.9 GB of system RAM. Mistral 7B needs 5.7 GB at Q4_K_M and uses 7.7 GB of system RAM.
When running text models, remember the context length caveat. The memory numbers listed here are for a standard 4k context window. If you increase the context window to process longer documents, the model will require significantly more memory and may no longer fit on your card.