NVIDIA GeForce RTX 3080
Hacker ApprovedRanked 16 of 42 graphics cards by recommenders
Popular for running local AI models at useful speeds and still fast after years. Main caveat: high power draw and heat.
Popular for running local AI models at useful speeds and still fast after years. Main caveat: high power draw and heat.
19 people gave an opinion
- recommend it
- 15
- criticize it
- 4
- approval share
- 79%
Recommended in 9 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 15 people recommend itNeeds 10 or more, met.
- 3.8 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
Runs local AI models well
“I run qwen3.5-9B on an RTX 3080 with 10GB of vram. It runs at ~77tk/s with around 50k context size.”
Comment from 17 Aug 2026 in “Qwen 3.8 27B is excellent, but it defaults to overthinking things” “Get a couple of them and you can probably run Qwen3.8-27B at a reasonable speed.”
Comment from 29 Aug 2026 in “Run Qwen3.8 27B locally: real numbers from my Mac Studio” “I average 80-120 tok/s on my RTX 3080 with gemma 4 and faster with Qwen 3.5.”
Comment from 3 Aug 2026 in “AirLLM 70B inference with single 4GB GPU” - Comment from 22 Apr 2026 in “Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model”
- Comment from 9 Mar 2026 in “How to run Qwen 3.5 locally”
Still feels new after years
“I've had a 3080 for 3 years and it still feels like a new card.”
Comment from 28 Jan 2026 in “Microsoft forced me to switch to Linux” “haven't had to do a single tweak this time.”
Comment from 3 Jan 2026 in “2026 will be my year of the Linux desktop” Good for hands-on tinkering
“If you already have an RTX 3080 it's absolutely worth the time to just mess around and see how it does”
Comment from 23 Jun 2026 in “Anthropic updates their terms to verify age or identity” “not very good but it was very fun and exciting to tinker with”
Comment from 25 Apr 2026 in “It's OK to Use Agentic to Revive the Projects You Never Were Going to Finish”
What people warn about
Each mark is one comment
Runs hot, draws high power
“My 3080 sffpc eats 70W idle and 400W under load.”
Comment from 15 Nov 2025 in “AMD continues to chip away at Intel's x86 market share” “My single 3080 runs so hot I don't need to warm my room in winter”
Comment from 27 Aug 2026 in “Small Models Have Arrived” Hibernation and driver stability issues
“those hibernation issues are related to corrupted graphics stacks because Nvidia”
Comment from 19 Dec 2025 in “The FreeBSD Foundation's Laptop Support and Usability Project” “My 3080 still has the occasional hiccup”
Comment from 26 Dec 2025 in “Asahi Linux with Sway on the MacBook Air M2”
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 3080This page | 15 | 4 | 79% | 9 | — | Approved |
What people said
18 of the 19 comments that mention it, newest first. Each links to the original comment.
“neither my 24GB RAM M4 Air nor my PC with a RTX3080 and 16GB of RAM seem usable (yet)”
“Get a couple of them and you can probably run Qwen3.8-27B at a reasonable speed.”
“My single 3080 runs so hot I don't need to warm my room in winter”
“I run qwen3.5-9B on an RTX 3080 with 10GB of vram. It runs at ~77tk/s with around 50k context size.”
“I average 80-120 tok/s on my RTX 3080 with gemma 4 and faster with Qwen 3.5.”
“If you already have an RTX 3080 it's absolutely worth the time to just mess around and see how it does”
“A couple of 3080 20GB's for cheap from China”
“if you go used you can get something like a 3080 instead”
“at the minimum 2x3080s (you need 2 to speed up prefill processing to build KV Cache)”
“not very good but it was very fun and exciting to tinker with”
“I'm able to get acceptable token generation speed (~55 tok/s) on a 3080”
“A 10GB 3080 still beats even an M2 Ultra with 192GB”
“using my 3080 with only 10 GB of RAM”
“I've had a 3080 for 3 years and it still feels like a new card.”
“haven't had to do a single tweak this time.”
“My 3080 still has the occasional hiccup”
“those hibernation issues are related to corrupted graphics stacks because Nvidia”
“My 3080 sffpc eats 70W idle and 400W under load.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.