# BitNet b1.58 2B4T

5 Hacker News commenters recommended BitNet b1.58 2B4T and 1 criticized it, November 2025 to November 2026. It was recommended in 4 of 13 months.

**Verdict:** Fast, memory-efficient model using about 400 MB of RAM and less training data; critics say factors left out of the paper make it less practical.

## Why people recommend it

- Low memory use during inference (2 comments): "it takes 1/6th as much memory during inference, and was trained on less than 1/4 the number of tokens" ([source](https://news.ycombinator.com/item?id=47337929)) "the model itself is super fast and efficient, and only takes about 400 MB of RAM" ([source](https://news.ycombinator.com/item?id=46862005))
- Impressive benchmark results (1 comments): "The new model they just released has impressive benchmark results" ([source](https://news.ycombinator.com/item?id=47337358))
- Fast and efficient (1 comments): "the model itself is super fast and efficient, and only takes about 400 MB of RAM" ([source](https://news.ycombinator.com/item?id=46862005))
- Trained on fewer tokens (1 comments): "it takes 1/6th as much memory during inference, and was trained on less than 1/4 the number of tokens" ([source](https://news.ycombinator.com/item?id=47337929))

## What people warn about

- Less practical than paper suggests (1 comments): "there are factors not considered in the paper which make it less practical than it seemed" ([source](https://news.ycombinator.com/item?id=48991394))

## Alternatives hackers recommend

- [Microsoft BitNet](https://hackerapproved.com/p/bitnet.md): 16 recommend
- [Ternary Bonsai](https://hackerapproved.com/p/ternary-bonsai.md): 14 recommend
- [Maple-Preview](https://hackerapproved.com/p/maple-preview.md): 6 recommend

## Cite as

Hacker Approved, "BitNet b1.58 2B4T", https://hackerapproved.com/p/bitnet-b1-58-2b4t/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).