Best local AI models for NVIDIA GTX 1650 SUPER

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.

ModelParametersBest quant that fitsMemory used at 4k
Lumina-Next / Lumina-Image 2.05BQ4_K_M3.7 GB
CogVideoX 2B / 5B5BQ4_K_M3.7 GB
DeepSeek-VL24.5BQ5_K_M3.8 GB
DeepFloyd IF4.3BQ5_K_M3.7 GB
Phi-3.5-vision4.2BQ5_K_M3.6 GB
Qwen3 4B4BQ6_K3.9 GB
Gemma 3 4B4BQ6_K3.9 GB
Gemma 4 E4B4BQ6_K3.9 GB
MiniCPM 3 4B4BQ6_K3.9 GB
Danube 3 4B4BQ6_K3.9 GB
Fish Speech 1.5 / OpenAudio S14BQ6_K3.9 GB
Phi-4-mini-instruct3.8BQ6_K3.7 GB
Phi-3.5 Mini3.8BQ6_K3.7 GB
OmniGen / OmniGen23.8BQ6_K3.7 GB
SD Cascade (Würstchen v3)3.6BQ6_K3.5 GB
SDXL Turbo3.5BQ6_K3.4 GB
SDXL Lightning3.5BQ6_K3.4 GB
ACE-Step3.5BQ6_K3.4 GB
MusicGen small/medium/large3.3BQ6_K3.2 GB
SmolLM3 3B3BQ8_03.8 GB
Replit Code v1.5 3B3BQ8_03.8 GB
Kandinsky 3.13BQ8_03.8 GB
Voxtral Mini / Small3BQ8_03.8 GB
Orpheus TTS3BQ8_03.8 GB
Higgs Audio v23BQ8_03.8 GB
Allegro2.8BQ8_03.6 GB
Open-Sora Plan2.7BQ8_03.4 GB
LFM2 1.2B / 2.6B2.6BQ8_03.3 GB
Playground v2.52.6BQ8_03.3 GB
Stable Diffusion 3.5 Medium2.5BQ8_03.2 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.

ModelParametersMemory at FP8 / optimizedSystem RAM at 4k
Stable Diffusion XL3.417B4.1 GB needed6.1 GB
Phi-3 Mini3.8B4.4 GB needed6.4 GB
Phi-4-multimodal5.6B4.1 GB needed6.1 GB
Magicoder-S-DS 6.7B6.7B4.9 GB needed6.9 GB
Mistral 7B7B5.7 GB needed7.7 GB
Qwen2.5 0.5B / 1.5B / 3B / 7B7B5.1 GB needed7.1 GB
OLMo 2 1B / 7B7B5.1 GB needed7.1 GB
Falcon 3 1B / 3B / 7B7B5.1 GB needed7.1 GB
Command R7B7B5.1 GB needed7.1 GB
OpenHermes 2.57B5.1 GB needed7.1 GB

How to read this

The NVIDIA GTX 1650 SUPER has 4 GB of GDDR6 memory. This memory size is the main limit for running local AI models. The model files must fit inside this video memory to run fast. If a model is too large for the video memory, it will either fail to load or run very slowly.

The quant column shows the quantization level for each model. Quantization reduces the size of a model by using fewer bits for the weights. A Q4_K_M quant uses about four bits per weight. A Q6_K quant uses about six bits, and a Q8_0 quant uses eight bits. Higher quants have better quality but require more memory. For example, Lumina-Next or Lumina-Image 2.0 at 5B fits in 3.7 GB using a Q4_K_M quant. Qwen3 4B, Gemma 3 4B, Gemma 4 E4B, MiniCPM 3 4B, Danube 3 4B, and Fish Speech 1.5 or OpenAudio S1 fit in 3.9 GB using a Q6_K quant. SmolLM3 3B fits in 3.8 GB using a Q8_0 quant.

You can run larger models by offloading parts of them to your system RAM. This CPU offload process lets you run models that exceed 4 GB, but it reduces generation speed. For these setups, we assume your computer has 32 GB of system RAM. Stable Diffusion XL needs 4.1 GB of video memory at FP8 or optimized settings, which requires 6.1 GB of system RAM. Phi-3 Mini needs 4.4 GB at Q4_K_M, which requires 6.4 GB of system RAM. Phi-4-multimodal needs 4.1 GB at Q4_K_M, which requires 6.1 GB of system RAM.

Other models also work well with CPU offload. Magicoder-S-DS 6.7B needs 4.9 GB at Q4_K_M and 6.9 GB of system RAM. Mistral 7B needs 5.7 GB at Q4_K_M and 7.7 GB of system RAM. Qwen2.5 7B, OLMo 2 7B, Falcon 3 7B, Command R7B, and OpenHermes 2.5 all need 5.1 GB at Q4_K_M and 7.1 GB of system RAM.

Memory usage calculations assume a standard 4k context window. If you increase the context window, the model will require more video memory. This extra memory is needed to store the active conversation history. Keeping the context at 4k or lower prevents out of memory errors on this hardware.