Mamba
Hacker ApprovedState-space model in AI tools
Sequence model architecture that people find fast and scalable for inference, with benchmark results roughly matching transformers. Critics note accuracy can degrade as context grows.
Sequence model architecture that people find fast and scalable for inference, with benchmark results roughly matching transformers. Critics note accuracy can degrade as context grows.
13 people gave an opinion
- recommend it
- 10
- criticize it
- 3
- approval share
- 77%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 10 people recommend itNeeds 10 or more, met.
- 3.3 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 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
Fast, efficient, and scales decently
“Modern implementation no longer have these problems and able to scale decently.”
Comment from 3 Feb 2026 in “The Core Flaws of Modern AI Based on Large Language Models” “It's apparently optimised for inference efficiency”
Comment from 18 Mar 2026 in “Mamba-3: Improved Sequence Modeling Using State Space Principles” “speed isn't a problem anymore - mamba is fast”
Comment from 28 Jan 2026 in “The C-Shaped Hole in Package Management” Competitive benchmark scores
“the perplexity is roughly the same and the benchmark scores are roughly the same”
Comment from 26 Oct 2026 in “Attention Is Not What You Need (2025)” “state-space models (Mamba) exhibit SOTA performance”
Comment from 23 Jun 2026 in “Munich 1991: The Roots of the Current AI Boom”
What people warn about
Each mark is one comment
No clear gain over transformers
“the perplexity is roughly the same and the benchmark scores are roughly the same”
Comment from 26 Oct 2026 in “Attention Is Not What You Need (2025)”
What people said
9 of the 13 comments that mention it, newest first. Each links to the original comment.
“the perplexity is roughly the same and the benchmark scores are roughly the same”
“state-space models (Mamba) exhibit SOTA performance”
“This is really promising.”
“mamba makes accuracy worse as context size grows”
“If you had worked on anything other than a transformer based architecture post 2016, such as Mamba or RWKV, you would have wasted your time.”
“It's apparently optimised for inference efficiency”
“Modern implementation no longer have these problems and able to scale decently.”
“speed isn't a problem anymore - mamba is fast”
“a badly compressed one in Mamba / SSM”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.