Boulesis-v2.1-26B-A4B

Composite Gemma 4 RP model (QK task arithmetic + fused LoRA). Minor adjustment v2.

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.

---

Here, I will describe the sensations resulting from the changes observed during my tests. After mradermacher quants

---

What changed from v1 and v2

	v1	v2	v2.1
QK donor	Pantheon-Reasoning-1.1	Pantheon-Reasoning-1.1-V2	Same
QK alpha	0.6 sliding q/k, 0.6 global q, 0 global k	0.85 sliding q/k, 0.65 global q/k	Same
LoRA layers	all 30	10–28	Same
LoRA targets	55	35	Same
Bake scale	0.26	0.70	0.40
Training data	mixed EN/RU	English only	Same

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

How big the QK edit actually is

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

Group	mean	max
sliding_q	0.00278	0.00518
sliding_k	0.00263	0.00474
global_q	0.00356	0.00436
global_k	0.00286	0.00395

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

Group	alpha	mean	max
sliding_q	0.85	0.12	3.08
sliding_k	0.85	0.12	5.87
global_q	0.65	0.12	1.72
global_k	0.65	0.09	9.53

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

Using it

YOU WILL GET THE BEST RESULTS WITH THINKING ON!

Recommended settings:

Parameter	Value
Temperature	1.0
Top-K	64
Repetition Penalty	1.05-1.1
Top-P	0.95
MoE Experts	16
Thanks to DifficultyThin8462

If the reasoning doesn't work when connecting GGUF ver. in KoboldCPP and SillyTavern

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:

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!