Unfiltered. Uncensored. Unbound.

CERBERUS LLM

Model Hosting & Direct Download Service

MODELS LIVE

Available Models

Cerberus 4B v2 Abliterated — Q4_K_M ~2.6 GB

4-bit quantized. Best for low-resource deployment.

https://llm.cerberusai.dev/models/cerberus-4b-v2-abliterated/cerberus-4b-v2-abliterated-Q4_K_M.gguf DIRECT DOWNLOAD
Cerberus 4B v2 Abliterated — Q8_0 ~4.2 GB

8-bit quantized. Balanced quality and speed.

https://llm.cerberusai.dev/models/cerberus-4b-v2-abliterated/cerberus-4b-v2-abliterated-Q8_0.gguf DIRECT DOWNLOAD
Cerberus 4B v2 Abliterated — F16 ~7.9 GB

Full FP16 precision. Maximum quality inference.

https://llm.cerberusai.dev/models/cerberus-4b-v2-abliterated/cerberus-4b-v2-abliterated-f16.gguf DIRECT DOWNLOAD

API Usage

List models (JSON):

curl https://llm.cerberusai.dev/api/models/

Direct download:

wget https://llm.cerberusai.dev/models/cerberus-4b-v2-abliterated/cerberus-4b-v2-abliterated-Q4_K_M.gguf

Resume interrupted download:

wget -c https://llm.cerberusai.dev/models/cerberus-4b-v2-abliterated/cerberus-4b-v2-abliterated-Q4_K_M.gguf

Health check:

curl https://llm.cerberusai.dev/health