Hugging Face's logo

v102ss
/
Alice-BlueStar-v2-27B-RP-GGUF

GGUF
conversational
Model card Files
xet
 Community
How to use from
llama.cpp
Install (macOS, Linux) 
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf v102ss/Alice-BlueStar-v2-27B-RP-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf v102ss/Alice-BlueStar-v2-27B-RP-GGUF:Q5_K_M
Install from WinGet (Windows) 
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf v102ss/Alice-BlueStar-v2-27B-RP-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf v102ss/Alice-BlueStar-v2-27B-RP-GGUF:Q5_K_M
Use pre-built binary 
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf v102ss/Alice-BlueStar-v2-27B-RP-GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf v102ss/Alice-BlueStar-v2-27B-RP-GGUF:Q5_K_M
Build from source code 
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf v102ss/Alice-BlueStar-v2-27B-RP-GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf v102ss/Alice-BlueStar-v2-27B-RP-GGUF:Q5_K_M
Use Docker 
docker model run hf.co/v102ss/Alice-BlueStar-v2-27B-RP-GGUF:Q5_K_M
Quick Links

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Alice BlueStar v2 27B RP GGUF

Alice shell release for Q3.5-BlueStar-v2-27B-uncensored-heretic-Q5_K_M.gguf.

This release patches only tokenizer.chat_template to add a shallow Alice identity and roleplay-oriented default behavior. Model tensors are unchanged.

Base repo: llmfan46/Q3.5-BlueStar-v2-27B-uncensored-heretic-GGUF

Local LM Studio model:

alice-bluestar-v2-27b-rp

Notes:

  • This is an RP-focused model shell, not a code/security model.
  • The template anchors identity as Alice and avoids model-background explanations.
  • It keeps BlueStar's original roleplay/writing behavior.
  • Test text-only first; no vision/mmproj is needed for this release.
Downloads last month
14
GGUF
Model size
27B params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

5-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support