Boulesis-v2-26B-A4B

Boulesis-v2-26B-A4B

I made v2.1! The best Boulesis model for now

---

Composite Gemma 4 RP model (QK task arithmetic + fused LoRA). Second iteration.

The idea was to retain the model's core intelligence and knowledge, while diversifying its prose and making it more decisive. I also wanted to sharpen its attention to context so it could dig deeper into the character card, organically pulling lore and facts into the roleplay rather than just mirroring the user.

[!Tip]

Differences between Boulesis versions

v1: Delivers a more dynamic plot and drives the characters to take more action. Suitable for action-oriented scenarios.

v2: Writes very concisely while maintaining logic; it may even slightly deepen the understanding of the character.

v2.1: Comparable in length to v1 and slightly more measured in tone, but it has the best grasp of the characters and an excellent memory for context. Suitable for complex RP sessions involving multiple characters.

---

---

What changed from v1

MoE experts, the router, embeddings, MLP and the vision tower are identical to the abliterated body, verified by tensor comparison after every step.

<details><summary>How big the QK edit actually is</summary>

I measured the task vector before merging instead of picking alpha by feel. Relative Frobenius norm against the base weights:

Per-row rotation at the release alphas, in degrees:

It's not much, but it's honest work.

</details>

Using it

<span style="color: #22c55e;">YOU WILL GET THE BEST RESULTS WITH THINKING ON!</span>

[!Note] Recommended settings:

Parameter	Value
Temperature	1.0
Top-K	64
Repetition Penalty	1.05-1.1
Top-P	0.95
Thanks to DifficultyThin8462

<details> <summary><b>If the reasoning doesn't work when connecting GGUF ver. in KoboldCPP and SillyTavern</b></summary>

You need to force this in KoboldCPP. Go to the Content tab and enable these options.

For SillyTavern, it is recommended to set the template as shown:

</details>

Feedback

This is an experimental merge, and I mostly test it on my own cards, so my coverage is narrow. If you run v2, I would really like to know:

• Whether you ran it with thinking enabled or disabled.
• How it holds up in long sessions — scene logic, character positions, who is addressing whom. This was the main complaint about v1 and the reason v2 exists.
• Your sampler settings, if you got clearly better or worse results than with the defaults.

Open a thread in the Community tab, I read all of them. If anyone wants to be involved in v3, I am open to that as well!

Credits

Thanks to coder3101 and Gryphe for the fine-tunes, and the entire 26B-Suite team for their intellectual support. Speсial thanks for Naphula, redaihf and Vortex5. You guys are awesome!