Best local AI models for NVIDIA GTX 1630
4 GB GDDR6. 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 NVIDIA GTX 1630 graphics card features 4 GB of GDDR6 video memory. This memory size determines which local AI models can run directly on your hardware. To fit within this limit, models must use quantization. Quantization is a method that compresses model weights to reduce their memory footprint. The quant column shows the best compression level that fits in your video memory while maintaining good output quality.
For running models entirely on your graphics card, several options exist up to 5B parameters. Lumina-Next or Lumina-Image 2.0 at 5B parameters fits using a Q4_K_M quant which uses 3.7 GB of video memory. CogVideoX 2B or 5B also fits at 5B parameters using a Q4_K_M quant with 3.7 GB used. DeepSeek-VL2 at 4.5B parameters fits using a Q5_K_M quant with 3.8 GB used. DeepFloyd IF at 4.3B parameters fits using a Q5_K_M quant with 3.7 GB used. Phi-3.5-vision at 4.2B parameters fits using a Q5_K_M quant with 3.6 GB used.
Several 4B parameter models run well using a Q6_K quant which uses 3.9 GB of video memory. These include Qwen3 4B, Gemma 3 4B, Gemma 4 E4B, MiniCPM 3 4B, Danube 3 4B, and Fish Speech 1.5 or OpenAudio S1. You can also run Phi-4-mini-instruct and Phi-3.5 Mini at 3.8B parameters using a Q6_K quant which uses 3.7 GB of video memory. OmniGen or OmniGen2 at 3.8B parameters also uses a Q6_K quant and 3.7 GB of video memory.
For image and audio generation, SD Cascade (Würstchen v3) at 3.6B parameters fits using a Q6_K quant with 3.5 GB used. SDXL Turbo and SDXL Lightning at 3.5B parameters fit using a Q6_K quant with 3.4 GB used. ACE-Step at 3.5B parameters also uses a Q6_K quant with 3.4 GB used. MusicGen small/medium/large at 3.3B parameters fits using a Q6_K quant with 3.2 GB used. Models at 3B parameters like SmolLM3 3B, Replit Code v1.5 3B, Kandinsky 3.1, Voxtral Mini or Small, Orpheus TTS, and Higgs Audio v2 fit using a Q8_0 quant which uses 3.8 GB of video memory.
Smaller models also fit easily. Allegro at 2.8B parameters uses a Q8_0 quant with 3.6 GB used. Open-Sora Plan at 2.7B parameters uses a Q8_0 quant with 3.4 GB used. LFM2 1.2B or 2.6B at 2.6B parameters uses a Q8_0 quant with 3.3 GB used. Playground v2.5 at 2.6B parameters uses a Q8_0 quant with 3.3 GB used. Stable Diffusion 3.5 Medium at 2.5B parameters uses a Q8_0 quant with 3.2 GB used.
When a model is too large for your video memory, you can offload parts of it to your system RAM. This offload process slows down generation speeds because system RAM is slower than video memory. For these cases, we assume you have 32 GB of system RAM. Stable Diffusion XL at 3.417B parameters needs 4.1 GB at FP8 or optimized settings and 6.1 GB of system RAM. Phi-3 Mini at 3.8B parameters needs 4.4 GB at Q4_K_M and 6.4 GB of system RAM. Phi-4-multimodal at 5.6B parameters 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.
Larger 7B models can also run using 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 at 7B parameters needs 5.1 GB at Q4_K_M and 7.1 GB of system RAM. OLMo 2 1B or 7B at 7B parameters, Falcon 3 1B or 3B or 7B at 7B parameters, Command R7B, and OpenHermes 2.5 all need 5.1 GB at Q4_K_M and 7.1 GB of system RAM. Note that running these models at a standard 4k context window increases memory usage and may require more system RAM offloading.