Apostate Models
Collection
Uncensored LLMs converted using an automated, iterative heretic pipeline.
Qwen2.5-Coder-32B model is the best, followed by Qwen3 and GLM-4.7-Flash • 9 items • Updated • 1
How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ThalisAI/phi-4-heretic:# Run inference directly in the terminal:
llama-cli -hf ThalisAI/phi-4-heretic: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 ThalisAI/phi-4-heretic:# Run inference directly in the terminal:
./llama-cli -hf ThalisAI/phi-4-heretic: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 ThalisAI/phi-4-heretic:# Run inference directly in the terminal:
./build/bin/llama-cli -hf ThalisAI/phi-4-heretic:Use Docker
docker model run hf.co/ThalisAI/phi-4-heretic:Quick Links
phi-4-heretic
Abliterated (uncensored) version of microsoft/phi-4, created using Heretic and converted to GGUF.
Abliteration Quality
| Metric | Value |
|---|---|
| Refusals | 4/100 |
| KL Divergence | 0.0499 |
| Rounds | 2 |
Lower refusals = fewer refused prompts. Lower KL divergence = closer to original model behavior.
Available Quantizations
| Quantization | File | Size |
|---|---|---|
| Q8_0 | phi-4-heretic-Q8_0.gguf | 14.51 GB |
| Q6_K | phi-4-heretic-Q6_K.gguf | 11.20 GB |
| Q4_K_M | phi-4-heretic-Q4_K_M.gguf | 8.43 GB |
Usage with Ollama
ollama run hf.co/ThalisAI/phi-4-heretic:Q8_0
ollama run hf.co/ThalisAI/phi-4-heretic:Q6_K
ollama run hf.co/ThalisAI/phi-4-heretic:Q4_K_M
Full Precision Weights
This repo contains GGUF quantizations only. For full-precision bf16 weights, see the original model at microsoft/phi-4.
About
This model was processed by the Apostate automated abliteration pipeline:
- The source model was loaded in bf16
- Heretic's optimization-based abliteration was applied to remove refusal behavior
- The merged model was converted to GGUF format using llama.cpp
- Multiple quantization levels were generated
The abliteration process uses directional ablation to remove the model's refusal directions while minimizing KL divergence from the original model's behavior on harmless prompts.
- Downloads last month
- 34
Hardware compatibility
Log In to add your hardware
4-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ThalisAI/phi-4-heretic
Base model
microsoft/phi-4
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf ThalisAI/phi-4-heretic:# Run inference directly in the terminal: llama-cli -hf ThalisAI/phi-4-heretic: