Best local AI models for NVIDIA 940M
2 GB DDR3. 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 NVIDIA 940M is an entry level laptop graphics card equipped with 2 GB of DDR3 video memory. Because local artificial intelligence models run directly on your hardware, this dedicated memory size is the main limit for your setup. To run a model entirely on your graphics processor, the model files and active memory must fit within this 2 GB boundary.
To make models fit onto this hardware, developers use quantization. The quant column shows the specific compression level used to shrink the model size. For example, the Allegro 2.8B model fits into 2 GB of video memory when using the Q4_K_M quantization. Other models like the SmolVLM 2B or Stable Diffusion 3 Medium use the Q6_K quantization to fit exactly 2 GB of video memory.
When a model exceeds your video memory, you must use CPU offload. This process splits the workload between your graphics card and your system RAM. If you have a system with 32 GB of system RAM, you can run larger models. For instance, the MusicGen small/medium/large 3.3B model needs 2.4 GB of video memory at Q4_K_M and requires 4.4 GB of system RAM to run.
CPU offload allows you to run advanced models like Stable Diffusion XL at 3.417B parameters using 4.1 GB at FP8 or optimized settings alongside 6.1 GB of system RAM. You can also run SDXL Turbo at 3.5B parameters which needs 2.6 GB at Q4_K_M and 4.6 GB of system RAM. However, offloading data to system RAM over the laptop system bus will significantly slow down your generation speeds.
You must also consider the context window when running local text models. The memory figures listed here represent the base model size. If you increase your active context window to 4k tokens, the system requires extra memory to store the conversation history. This extra memory usage can easily push a tight model over your 2 GB limit and trigger slow system RAM offloading.
For the best performance without offloading, look for models that leave a small safety margin. The TinyLlama 1.1B model at Q8_0 uses only 1.4 GB of video memory. This leaves 0.6 GB of free space on your NVIDIA 940M for context data and basic display tasks.