Hacker ApprovedDepartments

AMD Radeon RX 7900 XT

Ranked 37 of 42 graphics cards by recommenders

Cheap card with 20GB of VRAM that people use for running local AI models. Critics say 20GB is tight for long context, and some wish they had bought the XTX.

Cheap card with 20GB of VRAM that people use for running local AI models. Critics say 20GB is tight for long context, and some wish they had bought the XTX.

8 people gave an opinion

recommend it
6
criticize it
2
approval share
75%
Each figure is one person. RecommendsCriticizes

Recommended in 5 of 13 months

  1. November 2025: not recommended
  2. December 2025: recommended
  3. January 2026: not recommended
  4. February 2026: not recommended
  5. March 2026: not recommended
  6. April 2026: not recommended
  7. May 2026: not recommended
  8. June 2026: recommended
  9. July 2026: not recommended
  10. August 2026: recommended
  11. September 2026: recommended
  12. October 2026: recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 6 people recommend itNeeds 10 or more, not met.
  • 3 recommenders for every criticNeeds 2 to 1 or better, met.
  • Recommended in 5 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

  • Affordable entry to local AI

    “much more affordable if you're trying to dip your toes into localgen”

    Comment from 25 Oct 2026 in “Five Qwen3.8-27B models match Fable 5 Using GVS5H Harness”

    “I too purchased the 7900xt as it was cheap with a lot of vram.”

    Comment from 15 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet”
  • Good value sleeper card

    “I too purchased the 7900xt as it was cheap with a lot of vram.”

    Comment from 15 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet”

    “7900 XT is a sleeper card.”

    Comment from 18 Sep 2026 in “Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint”

What people warn about

Each mark is one comment

  • Wished for XTX's extra VRAM

    “should have forked over a couple hundred more and gotten the 7900XTX for the extra VRAM”

    Comment from 16 Jun 2026 in “Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?”

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.

AMD Radeon RX 7900 XT compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
NVIDIA GeForce RTX 30901162185%125 yrs14 ownersApproved
NVIDIA GeForce RTX 50901023773%121 yr3 ownersApproved
NVIDIA RTX PRO 6000772675%12—Approved
Nvidia GPUs676750%116 yrs3 owners—
AMD Radeon RX 7900 XTThis page6275%5——
See all 42 graphics cards, ranked

What people said

8 of the 9 comments that mention it, newest first. Each links to the original comment.

“much more affordable if you're trying to dip your toes into localgen”

RecommendsComment from 25 Oct 2026 in “Five Qwen3.8-27B models match Fable 5 Using GVS5H Harness”

“7900 XT is a sleeper card.”

RecommendsComment from 18 Sep 2026 in “Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint”

“20GB is just barely not enough unless you want to live with 32k context”

CriticizesComment from 17 Aug 2026 in “Qwen 3.8 27B is excellent, but it defaults to overthinking things”

“I too purchased the 7900xt as it was cheap with a lot of vram.”

RecommendsComment from 15 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet”

“unsloth/Muse-Glimmer-30B-GGUF:UD-Q4_K_XL runs on my 7900XT barely”

RecommendsComment from 10 Aug 2026 in “Meta Muse Glimmer – open weights 30B local coding model”

“Bad move. Should have used the money to buy NVIDIA stock”

CriticizesComment from 3 Aug 2026 in “Qwen3.8-Max: A New Bar for Coding and Cowork”

“should have forked over a couple hundred more and gotten the 7900XTX for the extra VRAM”

MixedComment from 16 Jun 2026 in “Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?”

“you're better off getting two AMD GPUs. Say a dual 7900XT would get way better performance.”

RecommendsComment from 15 Jun 2026 in “Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.