[VladVladikoff]

Maybe I’m missing it but the page is really light on technical information. Is this a quantized / distilled model of a larger LLM? Which one? How many parameters? What quantization? What T/s can I expect? What are the VRAM requirements? Etc etc

[NitpickLawyer]

You can see what it uses here - https://github.com/ente-io/ente/blob/main/web/apps/ensu/src/...

Either LFM2.5-1.6B-4bit or Qwen3.5-2B-8bit or Qwen3.5-4B-4bit

[sync]

Hmm, the Mac app downloaded gemma-3-4b-it-Q4_K_M.gguf for me (on an Apple M4) - maybe the desktop apps download different models?

Though, I don't see any references to Gemma at all in the open source code...

[embedding-shape]

Huh, 1.6B/2B/4B models, I guess they weren't joking when they said "not as powerful as ChatGPT or Claude Code". Also unsure why they said "Claude Code", it's not an CLI agent AFAIK?

[dr_kiszonka]

I so wanted to love Liquid AI's models, but despite their speed I was never able to get anything useful out of them. Even their larger models can't be trusted with simple stuff like inserting a column into a markdown table. The advertised tool calling is also not great. What I found interesting was that the ones I tried were a little light on guardrails.

I would really like to know what people use these small and tiny models for. If any high-karma users are reading it, would you consider posting Ask HN?

[dgb23]

This seems to be a general chat app, but otherwise small models can be very effective within the right use cases and orchestration.

[embedding-shape]

> otherwise small models can be very effective within the right use cases and orchestration

very limited amount of use cases, perhaps. As a generalized chat assistant? I'm not sure you'd be able to get anything of value out from them, but happy to be proven otherwise. I have all of those locally already, without fine-tuning, what use case could I try right now where any of those are "very effective"?

[dgb23]

Judging from my experimentation with local models:

You can use a small coding model to produce working code with a deterministic workflow (ex: state machine) if you carefully prune the context and filter down what it can do per iteration. Instead of letting it "reason" through an ever growing history, you give it distinct piecemeal steps with tailored context.

I think this can be generalized to:

Anything that can be built from small, well understood pieces and can be validated and fixed step by step. Then the challenge becomes designing these workflows and automating them.

(I'm not there yet, but one thing I have in mind might be a hybrid approach where the planning is produced by a more expensive model. The output it has to produce are data driven state machines or behavior trees (so they can be validated deterministically). Then it offloads the grunt work to a small, local model. When it's done, the work gets checked etc.)

[Mashimo]

> Also unsure why they said "Claude Code", it's not an CLI agent AFAIK?

Claude Code is a Desktop app as well.

[yomismoaqui]

The consfusing way AI companies like to name products is something to be studied.

[Oxodao]

tbf they're not the only one doing so, we had 3 different "Microsoft Teams" and "Outlook" until recently...

[embedding-shape]

Ok, but "Claude Code"/"Claude Desktop" regardless is software, a tool, not a model/LLM. Doesn't make much sense as they've written it.

[Mashimo]

For the end user who just installs the app it's probably all the same. It's not a technical document.

For the user it's just important that the small grimlin that sits in the Ente app is not as smart as the grimlin that sits in the Claude app.

[lancekey]

I don’t think so. IIRC the desktop app is called Claude and it has a code option in the UI.

[anthuswilliams]

Claude Cowork (part of the Desktop app) is claude code, running inside a VM.

Helpful writeup here: https://pvieito.com/2026/01/inside-claude-cowork (I am not the author)

[Mashimo]

If you go to the product website: https://claude.com/product/claude-code

> Use Claude Code where you work

> Desktop Termianl IDE WEb and iOS Slack

Not that it is important any way ¯\_(ツ)_/¯

[woadwarrior01]

The only takeaway for me from this is that the Ente is at < $10m/year in revenue. Because the LFM model license has a commercial use threshold of $10m.

https://www.liquid.ai/lfm-license

[hellcow]

I tried it on my iPhone 13 mini. I believe the model you get changes depending on your phone specs. For me it downloaded a ~1.3GB model which can speak in complete sentences but can’t do much beyond that. Can’t blame them though—that model is tiny, and my device wasn’t designed for this.

[ahofmann]

I have the same questions. After installing the app, it downloads 2.5 GB of data. I presume this is the model.