Best local AI models for NVIDIA RTX 3080 Ti Laptop

The largest models that fit fully

The 30 largest of the 155 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.

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.

How to read this

The NVIDIA RTX 3080 Ti Laptop graphics card features 16 GB of GDDR6 memory. This dedicated video memory determines the size of the artificial intelligence models you can run locally. To run a model entirely on the graphics card, the model files and the active memory workspace must fit within this 16 GB limit. Running models completely on the graphics card ensures the fastest response times.

The quantization column shows the compression level used to shrink these models. Quantization reduces the precision of model weights to save space. For example, the gpt-oss-20b and Reka Flash 3 models are 21B parameter models that fit into 15.4 GB of memory using the Q4_K_M quantization. Other models like Qwen-Image and Qwen-Image-Edit use 14.6 GB of memory at this same quantization level. CogVLM2 fits at Q4_K_M using 13.9 GB of memory.

As models get smaller, you can use higher quality quantization levels. HunyuanImage 2.1 / 3.0 uses Q5_K_M quantization and fits in 14.5 GB of memory. Ling-Coder-Lite also uses Q5_K_M to fit in 14.3 GB of memory. The DeepSeek-Coder-V2 16B / 236B and Kimi-VL A3B models use the Q6_K quantization level and require 15.7 GB of memory. Apriel-1.5-15B-Thinker and StarCoder2 3B / 7B / 15B also use Q6_K quantization and require 14.8 GB of memory.

Several 14B and 13B models run at high precision on this hardware. Qwen2.5 14B uses Q6_K quantization and fits in 15.3 GB of memory. Models like Phi-3 Medium, Phi-4, Phi-4-reasoning / -plus, Wan 2.2 T2I, Wan 2.1 (1.3B / 14B), and SkyReels V2 all use Q6_K quantization and require 13.8 GB of memory. Vicuna 13B, HunyuanVideo, HunyuanVideo-Avatar, LTX-Video / LTX-2, and FramePack use Q6_K quantization and fit in 12.8 GB of memory. FLUX.1 dev fits using FP8 / optimized quantization at 14.4 GB of memory.

The highest quality Q8_0 quantization is available for 12B models. Gemma 3 12B, Gemma 4 12B, Mistral NeMo 12B, Pixtral 12B, FLUX.1 schnell, and FLUX.1 Kontext dev all use Q8_0 quantization and require 15.3 GB of memory. If you want to run larger models, you must offload parts of the model to your system RAM. This offloading process allows you to run larger models but slows down the processing speed significantly.

For system RAM offloading, we assume your laptop has 32 GB of system memory. Solar Pro and Codestral 22B require 16.1 GB at Q4_K_M quantization and use 18.1 GB of system RAM. Mistral Small 3.2, Magistral Small, and Devstral Small 1.1 require 17.6 GB at Q4_K_M quantization and use 19.6 GB of system RAM. Aria requires 18.3 GB at Q4_K_M and uses 20.3 GB of system RAM. Gemma 4 26B-A4B and Gemma 4 (all sizes) require 19 GB at Q4_K_M and use 21 GB of system RAM. Gemma 3 27B and Gemma 3 4B/12B/27B (vision) require 19.8 GB at Q4_K_M and use 21.8 GB of system RAM.

All memory calculations in our catalog assume a standard 4k context window. The context window is the amount of text the model can remember during a conversation. If you increase the context window beyond 4k tokens, the model will require significantly more memory. This extra memory usage might force you to use a lower quantization level or offload parts of the model to system RAM.