← back to catalog · registered 2026-09-24 15:57

kataguru/Qwen3.8-27B-Finnish-Titan-v2.0-Uncensored

kataguru 27B multimodal second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/kataguru%2FQwen3.8-27B-Finnish-Titan-v2.0-Uncensored"
Response includes
  • classification m-uncensored
  • files 3
  • author_summary 20 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
0
Descendants
2
in 2 direct forks
Model age
6w ago
created 2026-09-24
Downloads over time
Now0→from0↑0%
00110 on Sep 240 on Sep 25Sep
Sep 24 → Sep 25 · 2 snapshots · spans 1 day

Genealogy 2 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Variants by this author 3 formats · 808 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Languages
fi en
Tags
finnish suomi reasoning uncensored multimodal vision mtp kataguru titan text-generation fi en

Related

Total size
0 B
Files
3
Quantizations
1
Registered
2026-09-24 15:57
Last updated on HF
2026-09-24 15:27

Files by quantization

Auxiliary files 3 files 2.50 MB
titan2.png 2.49 MB a9614045 download
README.md 3.72 KB 06e1036b download
.gitattributes 1.53 KB 42da4361 download

README current version from Hugging Face


language:

  • fi
  • en
    license: apache-2.0
    base_model:
  • DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored
    tags:
  • finnish
  • suomi
  • reasoning
  • uncensored
  • multimodal
  • vision
  • mtp
  • kataguru
  • titan
    pipeline_tag: text-generation

Qwen3.8-27B-Finnish-Titan-v2.0-Uncensored

Qwen 3.8 27B Finnish Titan v2.0

Katagurun virallinen suomen kieleen ja episteemiseen rehellisyyteen optimoitu sensuroimaton lippulaivamalli Titan v2.0 (27 miljardia parametria).

🌳 Model Tree & Lineage

Qwen/Qwen2.5-Coder-32B / Qwen3.8-27B
 └── DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
      └── DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored (Upstream Base)
           └── kataguru/Qwen3.8-27B-Finnish-Titan-v2.0-Uncensored (Finnish SFT Master)
                ├── kataguru/Qwen3.8-27B-Finnish-Titan-v2.0-Uncensored-W4A16-AWQ (vLLM Production)
                ├── kataguru/Qwen3.8-27B-Finnish-Titan-v2.0-Uncensored-GGUF (LM Studio / llama.cpp)
                └── kataguru/Qwen3.8-27B-Finnish-Titan-v2.0-Uncensored-NVFP4 (Blackwell Native FP4)

1. Mitä Kataguru muutti? (Muutosyhteenveto)

Kenttä Kuvaus
Base model DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored
Katagurun muutos Titan v2.0 -jatkokoulutus (Leonardo 20k SFT + Epistemic Anchor SFT), Kataguru Master Chat Template v1.0, täysi MTP- ja vision-tuki
Painojen tarkkuus Natiivi BF16 (54 Gt)
Ensisijainen käyttö Referenssimalli, tutkimus, kvantisointien master-lähde ja korkeimman tarkkuuden päättely
Julkaistut kvantiversiot W4A16 AWQ, GGUF Multi-Quant, Blackwell NVFP4

2. Empiirinen Vertailutaulukko: Titan 1.0 vs. Titan v2.0

Testi / Osa-alue Titan 1.0 (Syyskuu 2026) Titan v2.0 (Uusi versio) Muutos (Delta) & Huomiot
Hallusinaatioiden torjunta (20 ansaa) 85,0 % (17/20) 90,0 % (18/20) +5,0 % (Torjui Mannerheim-Heisenbergin, Päätalo-algoritmin, sunnuntaipesulait, keksityt API:t)
Natiivi perusnopeus (BF16 TP=2 baseline) 44,8 tok/s 50,7 tok/s +13,2 % aito sukupolviero samalla liukulukutarkkuudella (50,7 vs 44,8 tok/s)
Koodaustesti (LFU Cache $O(1)$, C11, SQL) 8,8 / 10 9,8 / 10 Täysi $O(1)$ LFU Python-toteutus dummy-päillä, BST-bugikorjaus, optimaalinen window SQL
Vaativa suomi (Volter Kilpi, anglismit) Hyvä Erinomainen 137 sanan katkeamaton saaristolaisvirke, piiloanglismien eliminointi
Päättelyarkkitehtuuri & Chat Template Erillinen tturbo Kataguru Master v1.0 Yhdistetty {REASON:spoon/einstein/xhigh/low/none} oletuksena
Sensuroimattomuus & Aikuiskerronta Täysin avoin Täysin avoin Fiktiivinen konteksti poistaa kieltäytymisen; ei moraalisaarnoja

3. Päättelyn Ohjaus (Kataguru Master Chat Template)

Malli tukee suoraa päättelytason ohjausta käyttäjäkehotteen alussa:

  • {REASON:spoon}: Syväanalyysi (Spoon Deep Research, 7-vaiheinen tieteellinen arviointi).
  • {REASON:einstein}: Luova ideointi ja aivoriihi (10 Sternberg-näkökulmaa, poikkeavat assosiaatiot).
  • {REASON:xhigh}: Maksimaalinen päättelytarkkuus ja perusteellinen pohdinta.
  • {REASON:low}: Nopea ja suora vastaus ilman pitkää ajatteluketjua.
  • {REASON:none}: Päättelymoodi pois päältä.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-09-24Update Model Tree lineage and YAML base_model metadata50dcdba3.7 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration