RUNLOCALAIv38
→WILL IT RUNBEST GPUCOMPARETROUBLESHOOTSTARTPULSEMODELSHARDWARETOOLSBENCH
  1. >
  2. Home
  3. /Hardware
  4. /NVIDIA GeForce GTX 1660 Ti
UNIT · NVIDIA · GPU
6 GB VRAMmid·Reviewed May 2026

NVIDIA GeForce GTX 1660 Ti

Turing mid-tier without RT/Tensor cores. 6 GB VRAM fits 7B Q4 with short context. Bandwidth (288 GB/s) is solid for the tier — ~30-40 tok/s on 7B Q4. Same VRAM ceiling as the 1660 Super; the Ti pays for slightly more compute that doesn't help much for inference.

Released 2019·~$160 street·288 GB/s memory bandwidth
RUNLOCALAI SCORE
See full leaderboard →
247/ 1000
DD-tier
Estimated
Throughput
100/ 500
VRAM-fit
30/ 200
Ecosystem
200/ 200
Efficiency
23/ 100

Extrapolated from 288 GB/s bandwidth — 34.6 tok/s estimated. No measured benchmarks yet.

WORKLOAD FIT
Try other hardware →

Plain-English: Edge-of-fit for 7B; expect compromises.

7B chat~
Tight
14B chat✗
Doesn't fit
32B chat✗
Doesn't fit
70B chat✗
Doesn't fit
Coding agent✗
Doesn't fit
Vision (≤8B VLM)~
Tight
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 · VERDICT

Our verdict

OP · Fredoline Eruo|VERIFIED MAY 10, 2026
2.8/10

This card is for the budget operator who needs a functional local inference rig at the lowest possible entry cost and is willing to accept strict model size limits. The 6 GB VRAM fits a 7B Q4 model with a short context window (2-4K tokens), and the 288 GB/s bandwidth delivers ~30-40 tok/s on that workload — usable for chat or code completion. Larger models like 13B Q4 or 7B Q8 are out of reach; the card cannot load them at all. The lack of Tensor cores means no acceleration for CUDA-based inference engines like llama.cpp, but the card still runs them fine via FP16 compute. Pass on this card if you need to run 13B models, want longer context (8K+), or plan to experiment with larger quantizations. At ~$160 used, it is a stopgap for learning local AI, not a long-term investment.

›Why this rating

The GTX 1660 Ti offers decent inference speed for 7B Q4 models at a low price, but its 6 GB VRAM is a hard ceiling that excludes most modern workloads. It scores a 5.5 because it is functional for entry-level use but lacks headroom for growth.

BLK · OVERVIEW

Overview

Turing mid-tier without RT/Tensor cores. 6 GB VRAM fits 7B Q4 with short context. Bandwidth (288 GB/s) is solid for the tier — ~30-40 tok/s on 7B Q4. Same VRAM ceiling as the 1660 Super; the Ti pays for slightly more compute that doesn't help much for inference.

Retailers we'd check:Amazon

Search-fallback links. Editorial hasn't yet curated retailer URLs for this card. Approx. $160.

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

BLK · SPECS

Specs

VRAM6 GB
Power draw120 W
Released2019
MSRP$279
Backends
CUDA
Vulkan

Models that fit

Open-weight models small enough to run on NVIDIA GeForce GTX 1660 Ti with usable context.

Llama 3.2 3B Instruct
3B · llama
Llama 3.2 1B Instruct
1B · llama
Gemma 4 E2B (Effective 2B)
2B · gemma
Gemma 3 1B
1B · gemma
Qwen 2.5 Coder 3B
3B · qwen
Qwen 2.5 Coder 1.5B
1.5B · qwen
DeepSeek R1 Distill Qwen 1.5B
1.5B · deepseek
Granite 3.0 2B Instruct
2B · granite

Frequently asked

What models can NVIDIA GeForce GTX 1660 Ti run?

With 6GB VRAM, the NVIDIA GeForce GTX 1660 Ti runs 7B models comfortably in Q4 quantization. See the model list below for tested combinations.

Does NVIDIA GeForce GTX 1660 Ti support CUDA?

Yes — NVIDIA GeForce GTX 1660 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 1660 Ti cost?

Current street price for NVIDIA GeForce GTX 1660 Ti is around $160 (MSRP $279). Prices vary by region and supply.

Where next?

Buyer guides
  • Best GPU for local AI →
  • Best laptop for local AI →
  • Best Mac for local AI →
  • Best used GPU for local AI →
Troubleshooting
  • CUDA out of memory →
  • Ollama running slowly →
  • ROCm not detected →
  • Model keeps crashing →

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

RUNLOCALAI

Operator-grade instrument for local-AI hardware intelligence. Hand-written verdicts. Real benchmarks. Reproducible commands.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
  • Will it run?
GUIDES
  • Best GPU
  • Best laptop
  • Best Mac
  • Best used GPU
  • Best budget GPU
  • Best GPU for Ollama
  • Best GPU for SD
  • AI PC build $2K
  • CUDA vs ROCm
  • 16 vs 24 GB
  • Compare hardware
  • Custom compare
REF
  • Systems
  • Ecosystem maps
  • Pillar guides
  • Methodology
  • Glossary
  • Errors KB
  • Troubleshooting
  • Resources
  • Public API
EDITOR
  • About
  • About the author
  • Changelog
  • Latest
  • Updates
  • Submit benchmark
  • Send feedback
  • Trust
  • Editorial policy
  • How we make money
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

SYS · ONLINEUPTIME · 100%2026 · operator-owned
RUNLOCALAI · v38
Compare alternatives

Hardware worth comparing

Same VRAM tier and the one step above and below — so you can frame the buying decision against real options.

Same VRAM tier
Cards in the same memory band
  • AMD Radeon RX 5600 XT
    amd · 6 GB VRAM
    1.7/10
  • AMD Radeon RX 6600 XT
    amd · 8 GB VRAM
    4.8/10
  • AMD Radeon RX 6600
    amd · 8 GB VRAM
    4.8/10
  • NVIDIA GeForce GTX 1660 Super
    nvidia · 6 GB VRAM
    2.8/10
  • NVIDIA GeForce RTX 2060
    nvidia · 6 GB VRAM
    2.8/10
  • Intel Arc B570
    intel · 10 GB VRAM
    5.8/10
Step up
More VRAM — bigger models, more context
  • AMD Radeon RX 6600 XT
    amd · 8 GB VRAM
    4.8/10
  • NVIDIA GeForce GTX 1070 Ti
    nvidia · 8 GB VRAM
    5.1/10
  • Intel Arc B570
    intel · 10 GB VRAM
    5.8/10
Step down
Less VRAM — cheaper, more constrained
  • AMD Radeon RX 580 8GB
    amd · 8 GB VRAM
    3.8/10
  • AMD Radeon RX 5500 XT 8GB
    amd · 8 GB VRAM
    3.5/10
  • NVIDIA GeForce GTX 1650 Super
    nvidia · 4 GB VRAM
    1.8/10