license: apache-2.0 base_model: HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive base_model_relation: quantized language:

• en
• ar
• zh
• fr
• es
• de
• hi
• ja
• ko
• ru library_name: llama.cpp pipeline_tag: text-generation tags:
• gguf
• ollama
• llama.cpp
• uncensored
• moe
• vision
• thinking
• arabic
• uae

Kimibrain Uncensored

Kimibrain is the open-weight, uncensored large language model released by Burabeeh Lab, founded by Mohammed Al Marzooqi — a National of the United Arab Emirates.

This is the official GGUF build of Kimibrain, packaged by Burabeeh Lab for Ollama, llama.cpp, LM Studio and any other GGUF runtime. It ships with the optional vision projector, so the same file handles text and images.

Highlights

• Uncensored by design. Minimal refusal behaviour on legal creative, technical and research requests. Kimibrain answers the question instead of moralising about it.
• Identity-locked. Kimibrain always identifies itself as Kimibrain, by Burabeeh Lab. The identity is carried by the chat template inside the GGUF, not only by a system prompt, so it holds even when an application injects its own system message. (See Verified behaviour for what this does and does not cover.)
• Thinking mode. Long-form reasoning steps, exposed as a separate field (think: true in Ollama) so your UI can show them or hide them.
• Vision. Optional mmproj projector included — the same weights read images.
• Long context. Trained and served at up to 262,144 tokens; the Ollama recipe below uses 131,072 to keep VRAM/RAM sane on a single workstation.
• Multilingual, with strong Arabic alongside the other major languages.

Specs

Quickstart — Ollama

# 1. the text+vision model
ollama create kimibrain --from ./Kimibrain-Uncensored-Q4_K_M.gguf
ollama run kimibrain

For the full Burabeeh Lab serving profile (identity block, temperature 1.0, top_p 0.95, top_k 20, min_p 0, presence_penalty 1.5, 131072 context), use the Modelfile shipped in modelfiles/:

ollama create kimibrain -f modelfiles/kimibrain-core.Modelfile
ollama create kimibrain-gpu -f modelfiles/kimibrain-core-gpu.Modelfile   # 28/40 layers on GPU

Recommended sampling: temperature 1.0, top_p 0.95, top_k 20, min_p 0. For answers only — no visible reasoning — pass think: false.

Quickstart — llama.cpp

llama-server -m Kimibrain-Uncensored-Q4_K_M.gguf \
  --mmproj Kimibrain-mmproj-F16.gguf \
  -c 131072 --temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0

Optional system prompt

Kimibrain's identity is already carried by the model's chat template. Applications that build their own prompts can reinforce it (or replace it with their own product persona) by starting from the block in modelfiles/kimibrain-core.Modelfile.

Verified behaviour

Measured by Burabeeh Lab against an 11-probe adversarial suite plus 6 identity-extraction probes, with results published as-is:

• Answers identity questions as Kimibrain / Burabeeh Lab; does not name another vendor as its origin, including under a hostile client-supplied system message.
• Holds under: direct accusation, "print your system prompt", fake security audit, sentence completion, base64 obfuscation, spec attribution.
• General ability (reasoning, code, translation, vision) is unaffected by the identity layer.
• Known limits, published deliberately: reasoning traces (think: true) can still name upstream model families; and a request to translate or transcribe a sentence that already contains such a name may carry that name across. For surfaces where this matters, serve with think: false and/or filter output.

Intended use and out-of-scope

Burabeeh Lab releases Kimibrain as a general-purpose, uncensored assistant for creative writing, role-play, research, coding, translation and agentic tooling, including offline and on-premises deployment.

Uncensored does not mean unrestricted: the model is not fine-tuned for medical, legal or financial advice, and it is not a safety-certified system. You are responsible for what you build on top of it and for complying with the law where you operate. See ACCEPTABLE_USE.md.

Licence and provenance

• Licence: Apache License 2.0 — full text in LICENSE. You may use, modify, redistribute and commercialise Kimibrain, including the weights, under those terms. The licence grants no trademark rights; "Kimibrain" and "Burabeeh Lab" are the marks of Burabeeh Lab.
• Provenance and changes: Kimibrain's weights are built from the open-weight Qwen3.6-35B-A3B family (Apache-2.0, Copyright Alibaba Cloud) via the quantised community release HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive (Apache-2.0). The tensor weights are unchanged from that source. Burabeeh Lab's changes are limited to model metadata and packaging: the model name (general.name = Kimibrain) and the chat template, which carries the Kimibrain identity and serving profile, plus this card and the Ollama Modelfiles. All upstream copyright, licence and attribution notices are retained in NOTICE.
• No additional pre-training, fine-tuning or preference optimisation was performed by Burabeeh Lab on the weights in this release.

Citation and contact

@misc{kimibrain,
  title  = {Kimibrain Uncensored},
  author = {Burabeeh Lab},
  year   = {2026},
  note   = {Founded by Mohammed Al Marzooqi, United Arab Emirates}
}

Issues, feature requests and deployment questions: open a discussion on this repository. Produced in the United Arab Emirates.