h14h

Speed.

Terra 6.1 on low reasoning outperforms Luna 6 on max reasoning, while costing half as much per task and completing each task over 10x faster (per AA v5).

Luna 6.1 will likely close the intelligence & cost gaps, but that speed advantage will remain.

I think for the majority of the audience here who use these models inside of coding agent harnesses w/ subsidized monthly subscriptions, there likely isn't one. Depending on how Terra contributes to the rate limits, it may make sense to use it for some subset of a repeated workflow to get more mileage out of sub.

If you pay API prices for inference in your product stack & have specific use-cases w/ custom evals, these smaller models provide an additional cost/speed lever to adjust. Ultimately, I think the point is to compete on cost for use-cases where Sol on the lowest reasoning is overkill.

If you have a fairly straightforward usecase where Terra performs just as well as Sol, but is faster and cheaper, why not use it?

watch it somehow use 20x more tokens tho

This is a big part of why React Native (and especially EAS) is still my preferred native development platform. The ability to ship OTA updates directly without depending on platform reviews & rollout schedules is a killer feature I'm not sure I could live without.

I'm excited for this style of agent to become more commoditized. I got access to Instinct recently and quickly found some pretty compelling use-cases for it. Namely, preparing my contracting invoices & drafting outgoing emails for me.

The onboarding experience of answering a WhatsApp message asking simply "what have you been putting off?" was pretty slick. Now I just want to see a version I can run on my own hardware so I don't have to worry about some sketchy company hoarding my data.

I know OpenClaw and Hermes are supposedly answers to this, but I find that they've each become so bloated with features that they're far more difficult to use and bug prone than I'm happy with. I'd prefer something more opinionated that limits the surface area for bugs as well as the number of decisions I need to make as an operator.

Historically I'd agree, but I push back on this for two reasons:

1. AI Agents (which are at the center of Omarchy) arguably make just about anyone a "developer" in the conventional sense, and potentially more willing to use a dev-forward desktop 2. Converting the types of devs who've been stuck on MacOS for years because they're neurotic about UI/UX "polish" could be a great way to smooth out Linux's many rough edges

IMO the biggest hurdle with building "a Linux desktop for everyone else" is QA. Discovering and fixing the random little bugs that only surface from millions of slightly different hardware/software configurations is a massive undertaking that I'm not sure can be easily brute-forced.

Alternatively, I see a lot of value in building an exciting desktop that attracts a critical mass of folks who are comfortable diagnosing bugs, submitting clear diagnostic reports, or even fixing said bugs themselves, and willing to do that work (or delegate it to an AI agent) for free.

Even if Omarchy doesn't end up being the desktop "everyone else" actually uses, it could be a great first step towards building out the kind of community linux would need to ensure such a desktop meets the requisite user-friendliness standards.

I tried briefly to figure out how to get them to communicate in a way that would at least be visible in Telegram, but quickly concluded it'd require a lot of custom hackery.

Honestly I'm probably more likely to build my own OpenClaw-mini with a custom client app. Shoehorning client connectivity into an existing messaging app borderline feels more complicated than just having an LLM build a minimal client app from scratch with full awareness of the backend capabilities.

I've already been doing something very similar to this with OpenClaw, where I set up multiple different Telegram bots each with different system prompts to tune their personalty & behavior.

It's not trivial to do, and I never managed to get bot-to-bot communication working. Even with my janky setup, the experience is honestly pretty great. Grok Bot simplifies the setup for this about as far as I imagine is possible, and frankly it's a pretty slick experience.

I fully expect this paradigm to catch on quickly.

I love these smaller models for the added capability they can bring to older hardware.

Recently picked up a 2013 Mac Pro (the trashcan one) on eBay for $150, and the official 6-bit quant of 2.6B runs at 25-30 tok/s under llama.cpp on one of the D500 GPUs. After installing Ubuntu LTS I have myself a lovely (if somewhat inefficient) little homelab server.

Are you using it via the official DeepSeek API, or via a different model provider? If the former, it's worth noting that their cache read prices are one tenth that of every other provider ($0.0028/M vs $0.028/M), so folks who want to use a sovereign inference provider with a zero data retention policy likely won't see anywhere close to the same value.

This has me hopeful for Qwen3.8-27B!

Whether wiping your phone is a criminal act seems could be a legitimate question depending on the circumstances.

Whether authoring such a feature is itself a criminal act is an outrageous question, to which the answer should be an obvious, and emphatic "no".

> reasoning efficiency matters directly for how expensive a model actually is in real use

I have high hopes on this topic, given token efficiency seemed to be the primary (only?) goal of the K2.7 Code release.

Excited to see the signals that come out of the big eval/benchmark sites.