He got bought out
yuxinlu1: "I'm now working with a top-tier AI lab to give back to the open-source community. 🤝 Many of you have already noticed the side effects in v1 and v2 — and honestly they come down to just two things: (1) not enough compute, and (2) one person with limited expertise behind the whole thing. This collaboration solves both of those completely. And the benchmarks you care about will absolutely be addressed — the things I simply couldn't fully pull off before because of time and compute limits. The people working on this with me are PhDs from top universities, with seriously strong papers and citation records. Just think about that for a second: the people who actually build large models are now contributing to the open-source community together with me — that is genuinely wild. 🤯 We're in active discussions right now, and the project is still in the R&D phase, so I can't share specifics yet — but the moment I have news, you'll be the first to know. 🚀"
pack it up boys, he got bought out
the "Mythos/Fable" name washing worked out well for him
this is why we are seeing alot of these mythos finetunes popping up everywhere on the trending page
yuxinlu1: "I can't share specifics yet"
that's just the start, soon he won't even share a single model
I guess you just need deceptive marketing and benchmaxxing a certain niche benchmark (in this case tau2, whatever that is) to be bought out by a "top-tier AI lab" and "PhDs from top universities with SERIOUSLY STRONG papers and citation records"
this also goes to show the level of intelligence of the people who label themselves top-tier AI labs and PhDs from top universities, with seriously strong papers and citation records.
@arc2745 — thank you, this really means a lot. 💚
You're right that the open side feels shakier lately — 3.6 came out open, 3.7 is API-only for now.
Either way, I'm going to keep building these. It's what I do, and I really want to find out how far a small model can
go on the hardware people already own — I don't think we've hit that limit yet. And there are a lot of people putting
out capable models for free; as long as that keeps up, anyone can run something strong on their own machine.
v3 is underway, more benchmarks coming. Thanks again. 🙏
Any recommendations for hermes or opencode? I haven't had much success without 64k context in hermes, for example.
Hey! Both work with v2 since it's an OpenAI-compatible endpoint — here's what I'd tune for each.
On context: you're not imagining it. These agent harnesses have huge system prompts, and Hermes Agent piles persistent
memory + skills on top, so it genuinely eats context fast. 32k is the realistic floor and 64k is comfortable — below
that the system prompt crowds out your actual prompt and the model starts flailing. Good news is you have tons of
headroom: v2 goes up to 256k context, so just start llama-server with -c 65536 (or 32768 if VRAM is tight). The only
real cost is KV cache, which on a 12B is manageable.
On tool calling — this is the part people get wrong most. Gemma 4 has its own native tool format, so you want a server
that actually parses it:
- llama.cpp: llama-server --jinja is the most reliable — it has the proper parser for Gemma 4's native tool calls.
- Ollama: make sure you're on v0.21.0+, that version has the critical Gemma 4 tool-call fix opencode relies on.
- opencode with llama.cpp: in opencode.json set tool_call on and the toolParser to raw-function-call + json.
Sampling matters too — use temp 1.0, top_p 0.95, top_k 64, rep_pen 1.1. With no rep penalty it can fall into
repetition loops on long outputs.
One thing that really helps a 12B: keep the tool list small and give each tool explicit, exact parameter names in its
schema. Gemma 4 is sensitive to that, and a lean tool set cuts down on it inventing or mangling calls. v2's agentic
training is coding/terminal style, so it shines with a focused tool set more than a 15-tool mega-harness.
Thanks for the model and your contribution for the community, it means a lot!
A big thank you too !
I was waiting for the v2 since I tried the v1. You are part of the pioneers of something big, hats off 🍪