UNIT · NVIDIA · GPU
4 GB VRAMentryReviewed October 2026

NVIDIA GeForce GTX 1050 Ti

No editorial image yet — generic vendor mark shown. Credentials in spec table below.

Pascal-era entry GPU. 4 GB VRAM is the practical floor for any local model — fits 1-3B at Q4 with room for short context. CUDA-compatible but no FP16 acceleration on consumer Pascal, so quantized inference is the only viable path. The card families the second-hand floor for the 'do I need a new GPU?' audience.

Released 2016·Launch MSRP $139 (2016) · Now sells well below its launch price on the used market.·112 GB/s memory bandwidth
RUNLOCALAI SCORE
See full leaderboard →
198/ 1000
DD-tier
Estimated
Throughput
39/ 500
VRAM-fit
30/ 200
Ecosystem
200/ 200
Efficiency
14/ 100

Sub-scores sum to 283 / 1000. Headline = 283 × 0.70 (Estimated-confidence discount) = 198. This is an algorithmic performance-tier score — distinct from, and often lower than, the editorial “Our verdict” below, which weighs value and real-world fit (especially for hardware we haven’t measured yet). How scoring works →

Extrapolated from 112 GB/s bandwidth — 13.4 tok/s estimated. No measured benchmarks yet.

WORKLOAD FIT
Try other hardware →

Plain-English: Doesn't fit modern chat models usefully — vision models won't fit.

7B chat✗
Doesn't fit
14B chat✗
Doesn't fit
32B chat✗
Doesn't fit
70B chat✗
Doesn't fit
Coding agent✗
Doesn't fit
Vision (≤8B VLM)✗
Doesn't fit
Long context (32K)✗
Doesn't fit
✓Comfortable — fits with headroom
~Tight — works, no slack
△Marginal — needs aggressive quant
✗Doesn't fit usefully

Verdicts extrapolated from catalog VRAM + bandwidth + ecosystem flags. Hover any chip for the rationale. Want measured numbers? Submit your own run with runlocalai-bench --submit.

BLK · OVERVIEW

Overview

Pascal-era entry GPU. 4 GB VRAM is the practical floor for any local model — fits 1-3B at Q4 with room for short context. CUDA-compatible but no FP16 acceleration on consumer Pascal, so quantized inference is the only viable path. The card families the second-hand floor for the 'do I need a new GPU?' audience.

Retailers we'd check:Amazon

Search-fallback link — editorial hasn't yet curated a retailer URL for this card. Check the current price with the retailer.

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

BLK · SPECS

Specs

VRAM4 GB
Power draw (peak)75 W
Released2016
MSRP$139
Backends
CUDA
Vulkan

Models that fit

Open-weight models small enough to run on NVIDIA GeForce GTX 1050 Ti with usable context.

all-MiniLM-L6-v2
0.022B · other · fits by VRAM, no benchmark yet
Nomic Embed Text v1.5
0.137B · other · fits by VRAM, no benchmark yet
Kokoro 82M
0.082B · other · fits by VRAM, no benchmark yet
BGE Large EN v1.5
0.335B · other · fits by VRAM, no benchmark yet
Qwen 3 0.6B
0.6B · qwen · fits by VRAM, no benchmark yet
all-mpnet-base-v2
0.109B · other · fits by VRAM, no benchmark yet
XTTS v2
0.46B · other · fits by VRAM, no benchmark yet
BGE Reranker v2 M3
0.57B · other · fits by VRAM, no benchmark yet

Frequently asked

What models can NVIDIA GeForce GTX 1050 Ti run?

With 4GB VRAM, the NVIDIA GeForce GTX 1050 Ti runs small models (3B and under) at modest quantization. See the model list below for tested combinations.

Does NVIDIA GeForce GTX 1050 Ti support CUDA?

Yes — NVIDIA GeForce GTX 1050 Ti is an NVIDIA card with full CUDA support, the most mature local-AI backend. llama.cpp, Ollama, vLLM, and ExLlamaV2 all run natively.

How much does NVIDIA GeForce GTX 1050 Ti cost?

The NVIDIA GeForce GTX 1050 Ti launched at an MSRP of $139 in 2016. Now sells well below its launch price on the used market. Retail prices change often, so check the current price with a retailer before you buy.

Where next?

Buyer guides
Troubleshooting

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.