NVIDIA GeForce RTX 5060 Ti 16GB
Hacker ApprovedRanked 15 of 42 graphics cards by recommenders
People recommend it as a low-cost 16GB VRAM card for running local LLMs, and dual-card setups scale well. The common caveat is that local models can be slow for interactive work.
People recommend it as a low-cost 16GB VRAM card for running local LLMs, and dual-card setups scale well. The common caveat is that local models can be slow for interactive work.
17 people gave an opinion
- recommend it
- 16
- criticize it
- 1
- approval share
- 94%
Recommended in 9 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 16 people recommend itNeeds 10 or more, met.
- 16 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 9 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Good value for local AI
“The best value option if you're building from scratch is go with 5060 ti (16GB VRAM)”
Comment from 16 Jun 2026 in “Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?” “The entry-level RTX 5060 Ti runs circles around it with a $400 MSRP and 180w TDP.”
Comment from 10 Dec 2025 in “Qualcomm acquires RISC-V focused Ventana Micro Systems” “still a good experience for only a fraction of the price”
Comment from 24 Jun 2026 in “For Most of the World, Open-Source AI Is the Only Way Forward” - Comment from 15 Jun 2026 in “Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?”
Strong local LLM speeds with dual cards
“2x 5060ti 16gb and tensor parallelism 2 is pretty easy to set up in any ATX PC case.”
Comment from 10 Oct 2026 in “Nvidia in talks to acquire US 'open' model startup Reflection AI” “a multiple 5060ti + tensor split mode + MPT will hit ~100/TPS without problem”
Comment from 25 Jul 2026 in “Open-weight AI is having its Kubernetes moment. Let's not ruin it” “You can put together dual 5060 Ti or 5070 Ti systems to run local LLMs too.”
Comment from 29 Sep 2026 in “GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price” - Comment from 16 Jun 2026 in “Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?”
Runs Qwen and other local models
“Running Q3 on 5060ti with 64k context. It runs great”
Comment from 8 Sep 2026 in “Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses” “You can run local LLMs on a 5060 Ti.”
Comment from 7 Oct 2026 in “Anthropic reported diary entry to police, woman faces felony charge” “I run qwen3.8 on 5060ti 16G RAM”
Comment from 29 Aug 2026 in “Run Qwen3.8 27B locally: real numbers from my Mac Studio” Easy setup on Linux and ATX cases
“2x 5060ti 16gb and tensor parallelism 2 is pretty easy to set up in any ATX PC case.”
Comment from 10 Oct 2026 in “Nvidia in talks to acquire US 'open' model startup Reflection AI” “works smooth as butter on Arch+X11”
Comment from 15 Nov 2025 in “GNOME 50 completes the migration to Wayland, dropping X11 backend code”
What people warn about
Each mark is one comment
Slow for interactive use
“running it on electricity money, 20 minutes per task is rough for anything interactive”
Comment from 27 Mar 2026 in “$500 GPU outperforms Claude Sonnet on coding benchmarks” Wish for more than 16GB VRAM
“I wish I sprung for a 24gb vram card but I never thought the price difference would matter”
Comment from 29 Apr 2026 in “HERMES.md: Anthropic bug causes $200 extra charge, refuses refund”
Other graphics cards people recommend
The four most recommended other graphics cards, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3090 | 116 | 21 | 85% | 12 | 5 yrs14 owners | Approved |
| NVIDIA GeForce RTX 5090 | 102 | 37 | 73% | 12 | 1 yr3 owners | Approved |
| NVIDIA RTX PRO 6000 | 77 | 26 | 75% | 12 | — | Approved |
| Nvidia GPUs | 67 | 67 | 50% | 11 | 6 yrs3 owners | — |
| NVIDIA GeForce RTX 5060 Ti 16GBThis page | 16 | 1 | 94% | 9 | — | Approved |
What people said
16 of the 20 comments that mention it, newest first. Each links to the original comment.
“2x 5060ti 16gb and tensor parallelism 2 is pretty easy to set up in any ATX PC case.”
“You can run local LLMs on a 5060 Ti.”
“You can put together dual 5060 Ti or 5070 Ti systems to run local LLMs too.”
“Running Q3 on 5060ti with 64k context. It runs great”
“I run qwen3.8 on 5060ti 16G RAM”
“a multiple 5060ti + tensor split mode + MPT will hit ~100/TPS without problem”
“Meh. I'd rather have 2x RTX 5060 Ti.”
“still a good experience for only a fraction of the price”
“Dual 5060ti 16gb does over 100 tok/s on 35B A3B.”
“The best value option if you're building from scratch is go with 5060 ti (16GB VRAM)”
“I bet two 16gb 5060tis would do the same for ~1200.”
“I wish I sprung for a 24gb vram card but I never thought the price difference would matter”
“running it on electricity money, 20 minutes per task is rough for anything interactive”
“to get an Nvidia 5060 Ti 16 GB I'd have to pay over 500 EUR”
“The entry-level RTX 5060 Ti runs circles around it with a $400 MSRP and 180w TDP.”
“works smooth as butter on Arch+X11”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.