Best local AI models for AMD HD 7870M
2 GB GDDR5. At a 4k context, 56 of the 233 models in our catalog with verified parameter counts fit fully, up to Allegro at 2.8B parameters.
Check your own machine against every model →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.
| Model | Parameters | Best quant that fits | Memory used at 4k |
|---|---|---|---|
| Allegro | 2.8B | Q4_K_M | 2 GB |
| Open-Sora Plan | 2.7B | Q4_K_M | 2 GB |
| LFM2 1.2B / 2.6B | 2.6B | Q4_K_M | 1.9 GB |
| Playground v2.5 | 2.6B | Q4_K_M | 1.9 GB |
| Stable Diffusion 3.5 Medium | 2.5B | Q4_K_M | 1.8 GB |
| Canary 1B / Qwen-2.5B | 2.5B | Q4_K_M | 1.8 GB |
| SeamlessM4T v2 | 2.3B | Q5_K_M | 2 GB |
| Parler-TTS | 2.2B | Q5_K_M | 1.9 GB |
| Kimi K3 DSpark | 2.2B | Q5_K_M | 2 GB |
| SmolVLM 256M / 500M / 2B | 2B | Q6_K | 2 GB |
| Stable Diffusion 3 Medium | 2B | Q6_K | 2 GB |
| Pyramid Flow | 2B | Q6_K | 2 GB |
| Wav2Vec2 / XLS-R | 2B | Q6_K | 2 GB |
| Moondream 2 | 1.9B | Q6_K | 1.9 GB |
| Qwen3 1.7B | 1.7B | Q6_K | 1.7 GB |
| SmolLM2 135M / 360M / 1.7B | 1.7B | Q6_K | 1.7 GB |
| StableLM 2 1.6B | 1.6B | Q8_0 | 2 GB |
| Sana 0.6B / 1.6B | 1.6B | Q8_0 | 2 GB |
| Zonos 0.1 | 1.6B | Q8_0 | 2 GB |
| Dia 1.6B | 1.6B | Q8_0 | 2 GB |
| Whisper Large v3 | 1.55B | Q8_0 | 2 GB |
| ControlNet / T2I-Adapter / IP-Adapter | 1.5B | Q8_0 | 1.9 GB |
| Hunyuan-DiT | 1.5B | Q8_0 | 1.9 GB |
| Stable Video Diffusion | 1.5B | Q8_0 | 1.9 GB |
| Whisper Large v2 / turbo | 1.5B | Q8_0 | 1.9 GB |
| AudioGen | 1.5B | Q8_0 | 1.9 GB |
| AudioLDM 2 | 1.5B | Q8_0 | 1.9 GB |
| Tango 2 | 1.4B | Q8_0 | 1.8 GB |
| TinyLlama 1.1B | 1.1B | Q8_0 | 1.4 GB |
| SantaCoder 1.1B | 1.1B | Q8_0 | 1.4 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 Q4_K_M | System RAM at 4k |
|---|---|---|---|
| SmolLM3 3B | 3B | 2.2 GB needed | 4.2 GB |
| Replit Code v1.5 3B | 3B | 2.2 GB needed | 4.2 GB |
| Kandinsky 3.1 | 3B | 2.2 GB needed | 4.2 GB |
| Voxtral Mini / Small | 3B | 2.2 GB needed | 4.2 GB |
| Orpheus TTS | 3B | 2.2 GB needed | 4.2 GB |
| Higgs Audio v2 | 3B | 2.2 GB needed | 4.2 GB |
| MusicGen small/medium/large | 3.3B | 2.4 GB needed | 4.4 GB |
| Stable Diffusion XL | 3.417B | 4.1 GB needed | 6.1 GB |
| SDXL Turbo | 3.5B | 2.6 GB needed | 4.6 GB |
| SDXL Lightning | 3.5B | 2.6 GB needed | 4.6 GB |
How to read this
The AMD HD 7870M is a mobile graphics card equipped with 2 GB of GDDR5 video memory. This hardware memory size is the absolute limit for running local AI models entirely on the graphics processor. When a model fits inside this 2 GB boundary, the GPU handles all computations quickly. If a model exceeds this limit, the system must split the workload.
To fit models into this limited space, developers use quantization. The quant column shows the specific compression level used to shrink the model. For example, the 2.8B Allegro and 2.7B Open-Sora Plan models use the Q4_K_M quant to fit exactly into 2 GB of video memory. Smaller models like the 1.7B SmolLM2 or 1.7B Qwen3 can run at a higher quality Q6_K quant while using 1.7 GB of video memory. The 1.1B TinyLlama uses the Q8_0 quant and requires only 1.4 GB of video memory.
When you want to run larger models, you must use CPU offloading. This process shares the workload between your GPU and your system RAM. For instance, running the 3B SmolLM3 or 3B Replit Code v1.5 at Q4_K_M requires 2.2 GB of video memory and 4.2 GB of system RAM. The 3.3B MusicGen requires 2.4 GB of video memory and 4.4 GB of system RAM. This setup works well if your computer has 32 GB of system RAM.
Offloading comes with a performance cost. Moving data between the graphics card and system memory is much slower than keeping everything on the GPU. While offloading allows you to run larger options like the 3.5B SDXL Turbo or 3.5B SDXL Lightning, your generation speeds will drop significantly compared to running smaller models fully on the GPU.
You must also consider the context window when running text models. The memory numbers listed here assume a standard 4k context window. If you increase the context length to process longer documents, the model will require more video memory. This extra memory demand can push a model over the 2 GB limit and trigger unexpected CPU offloading.