Check my GPU

Hardware · NVIDIA

What AI models can the NVIDIA GeForce RTX 3050 Ti Laptop GPU run?

VRAM
4.0 GB
Usable for models
4.0 GB
Memory bandwidth
192 GB/s
FP16 compute
5.3 TFLOPS
Released
2021

Specifications

MakerNVIDIA
TypeLaptop GPU (soldered memory)
Video memory (VRAM)4.0 GB
Usable for AI models4.0 GB
Memory bandwidth192 GB/s
FP16 compute5.3 TFLOPS
InterfacePCIe 4.0
Released2021

Best LLMs for the NVIDIA GeForce RTX 3050 Ti Laptop GPU

Grade · points Model Quant Memory Speed Fit
80 ptsGreat (A) · 80 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Gemma 4 E2BGoogle Q4_K_M 4.0 GB 46.0 tok/s Tight fit
80 ptsGreat (A) · 80 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3.5 4BAlibaba Q4_K_M 3.9 GB 50.6 tok/s Tight fit
80 ptsGreat (A) · 80 of 100 points: Model quality 26.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 TMax 4BAi2 Q4_K_M 3.6 GB 56.0 tok/s Tight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Agents-A1 4BInternScience Q4_K_M 3.8 GB 51.9 tok/s Tight fit
78 ptsGreat (A) · 78 of 100 points: Model quality 24.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Fara 1.5 4BMicrosoft Q4_K_M 3.8 GB 51.9 tok/s Tight fit
76 ptsGreat (A) · 76 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Nemotron 3 Nano 4BNVIDIA Q4_K_M 3.4 GB 59.4 tok/s Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 22.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Granite 4.2 3BIBM Q4_K_M 3.7 GB 64.4 tok/s Tight fit
75 ptsGreat (A) · 75 of 100 points: Model quality 21.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3 4B Thinking 2507Alibaba Q3_K_M 4.0 GB 75.8 tok/s Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 19.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 LFM2.5 2.6BLiquid AI Q6_K 3.1 GB 60.6 tok/s Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 20.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3 4B Instruct 2507Alibaba Q3_K_M 4.0 GB 75.8 tok/s Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Jamba Reasoning 3BAI21 Labs Q5_K_M 3.1 GB 60.8 tok/s Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 LFM2.5-VL 3BLiquid AI Q5_K_M 3.1 GB 62.4 tok/s Runs well

Best Image models for the NVIDIA GeForce RTX 3050 Ti Laptop GPU

Grade · points Model Precision Memory Time per output Fit
74 ptsGreat (A) · 74 of 100 points: Model quality 34.4/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15 FLUX.2 [klein] 4BBlack Forest Labs FP8 3.5 GB 9.2 s Tight fit
73 ptsGreat (A) · 73 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Realistic Vision V5.1SG161222 FP16 2.8 GB 9.4 s Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 DreamShaper 8Lykon FP16 2.8 GB 9.4 s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 22.5/45, Memory fit 20.0/25, Speed 13.5/15, Memory use 15.0/15 PixArt-Σ XL 1024PixArt FP16 3.3 GB 12 s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Stable Diffusion 1.5Stability AI / Runway FP16 2.8 GB 9.4 s Runs well
68 ptsGood (B) · 68 of 100 points: Model quality 35.2/45, Memory fit 10.0/25, Speed 8.6/15, Memory use 15.0/15 Z-Image TurboAlibaba (Tongyi) Q4 GGUF 3.5 GB 31 s Tight fit

Best Video models for the NVIDIA GeForce RTX 3050 Ti Laptop GPU

Grade · points Model Precision Memory Time per output Fit
56 ptsUsable (C) · 56 of 100 points: Model quality 15.8/45, Memory fit 12.0/25, Speed 14.1/15, Memory use 15.0/15 AnimateDiff v3 (SD 1.5)Shanghai AI Lab FP16 2.6 GB 3.4 min Runs well

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.