Best local AI models for NVIDIA GTX 1050 3GB
3 GB GDDR5. At a 4k context, 76 of the 233 models in our catalog with verified parameter counts fit fully, up to Qwen3 4B at 4B parameters.
Check your own machine against every model →The largest models that fit fully
The 30 largest of the 76 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 |
|---|---|---|---|
| Qwen3 4B | 4B | Q4_K_M | 2.9 GB |
| Gemma 3 4B | 4B | Q4_K_M | 2.9 GB |
| Gemma 4 E4B | 4B | Q4_K_M | 2.9 GB |
| MiniCPM 3 4B | 4B | Q4_K_M | 2.9 GB |
| Danube 3 4B | 4B | Q4_K_M | 2.9 GB |
| Fish Speech 1.5 / OpenAudio S1 | 4B | Q4_K_M | 2.9 GB |
| Phi-4-mini-instruct | 3.8B | Q4_K_M | 2.8 GB |
| Phi-3.5 Mini | 3.8B | Q4_K_M | 2.8 GB |
| OmniGen / OmniGen2 | 3.8B | Q4_K_M | 2.8 GB |
| SD Cascade (Würstchen v3) | 3.6B | Q4_K_M | 2.6 GB |
| SDXL Turbo | 3.5B | Q5_K_M | 3 GB |
| SDXL Lightning | 3.5B | Q5_K_M | 3 GB |
| ACE-Step | 3.5B | Q5_K_M | 3 GB |
| MusicGen small/medium/large | 3.3B | Q5_K_M | 2.8 GB |
| SmolLM3 3B | 3B | Q6_K | 3 GB |
| Replit Code v1.5 3B | 3B | Q6_K | 3 GB |
| Kandinsky 3.1 | 3B | Q6_K | 3 GB |
| Voxtral Mini / Small | 3B | Q6_K | 3 GB |
| Orpheus TTS | 3B | Q6_K | 3 GB |
| Higgs Audio v2 | 3B | Q6_K | 3 GB |
| Allegro | 2.8B | Q6_K | 2.8 GB |
| Open-Sora Plan | 2.7B | Q6_K | 2.7 GB |
| LFM2 1.2B / 2.6B | 2.6B | Q6_K | 2.6 GB |
| Playground v2.5 | 2.6B | Q6_K | 2.6 GB |
| Stable Diffusion 3.5 Medium | 2.5B | Q6_K | 2.5 GB |
| Canary 1B / Qwen-2.5B | 2.5B | Q6_K | 2.5 GB |
| SeamlessM4T v2 | 2.3B | Q8_0 | 2.9 GB |
| Parler-TTS | 2.2B | Q8_0 | 2.8 GB |
| Kimi K3 DSpark | 2.2B | Q8_0 | 2.9 GB |
| SmolVLM 256M / 500M / 2B | 2B | Q8_0 | 2.5 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-3.5-vision | 4.2B | 3.1 GB needed | 5.1 GB |
| DeepFloyd IF | 4.3B | 3.1 GB needed | 5.1 GB |
| DeepSeek-VL2 | 4.5B | 3.3 GB needed | 5.3 GB |
| Lumina-Next / Lumina-Image 2.0 | 5B | 3.7 GB needed | 5.7 GB |
| CogVideoX 2B / 5B | 5B | 3.7 GB needed | 5.7 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 |
How to read this
The NVIDIA GTX 1050 3GB graphics card features 3 GB of GDDR5 video memory. This memory limit determines which local AI models can run directly on your hardware. To fit inside this limit, models must use quantization. Quantization is a compression method that reduces the size of a model while keeping most of its capability. The best quant column shows the highest quality quantization level that fits within your video memory.
For models that fit entirely on the card, a 4B parameter model is the absolute limit. Models like Qwen3 4B, Gemma 3 4B, Gemma 4 E4B, MiniCPM 3 4B, Danube 3 4B, and Fish Speech 1.5 / OpenAudio S1 can run at the Q4_K_M quantization level. This setup uses 2.9 GB of your video memory. Models with 3.8B parameters like Phi-4-mini-instruct, Phi-3.5 Mini, and OmniGen / OmniGen2 also fit at Q4_K_M, using 2.8 GB of memory.
Slightly smaller models can use higher quality quantization levels. SDXL Turbo, SDXL Lightning, and ACE-Step are 3.5B parameter models that run at the Q5_K_M level using 3 GB of memory. MusicGen small/medium/large uses 2.8 GB at Q5_K_M. Models with 3B parameters like SmolLM3 3B, Replit Code v1.5 3B, Kandinsky 3.1, Voxtral Mini / Small, Orpheus TTS, and Higgs Audio v2 can run at the Q6_K level using 3 GB of memory.
Other options at the Q6_K level include Allegro at 2.8 GB, Open-Sora Plan at 2.7B parameters using 2.7 GB, and LFM2 1.2B / 2.6B or Playground v2.5 using 2.6 GB. Stable Diffusion 3.5 Medium and Canary 1B / Qwen-2.5B use 2.5 GB at Q6_K. For even higher precision, SeamlessM4T v2, Parler-TTS, and Kimi K3 DSpark use the Q8_0 level, requiring up to 2.9 GB. SmolVLM 256M / 500M / 2B uses 2.5 GB at Q8_0.
When a model is too large for the 3 GB video memory, you can offload parts of it to your system RAM. This process requires a system with 32 GB of system RAM. Offloading allows you to run larger models, but it costs performance because system RAM is much slower than video memory. For example, Mistral 7B needs 5.7 GB at Q4_K_M and requires 7.7 GB of system RAM to run.
Other offload options include Phi-4-multimodal at 4.1 GB video memory and 6.1 GB system RAM, or Magicoder-S-DS 6.7B at 4.9 GB video memory and 6.9 GB system RAM. You can also run CogVideoX 2B / 5B or Lumina-Next / Lumina-Image 2.0 using 3.7 GB video memory and 5.7 GB system RAM. DeepSeek-VL2 needs 3.3 GB video memory and 5.3 GB system RAM. Phi-3 Mini needs 4.4 GB video memory and 6.4 GB system RAM.
Please note the 4k context caveat. Running models with a large context window increases memory usage. If you generate long responses or input long texts, the model might exceed the 3 GB limit and crash. Keep your context lengths short to ensure stable performance on this card.