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 truthcoder/TC-Mini-0.6B-GGUF:
# Run inference directly in the terminal:
llama cli -hf truthcoder/TC-Mini-0.6B-GGUF:
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf truthcoder/TC-Mini-0.6B-GGUF:
# Run inference directly in the terminal:
llama cli -hf truthcoder/TC-Mini-0.6B-GGUF:
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf truthcoder/TC-Mini-0.6B-GGUF:
# Run inference directly in the terminal:
./build/bin/llama cli -hf truthcoder/TC-Mini-0.6B-GGUF:
Use Docker
docker model run hf.co/truthcoder/TC-Mini-0.6B-GGUF:
Quick Links

TC Mini 0.6B โ€” GGUF (Ollama ยท LM Studio ยท llama.cpp)

Private AI that runs fully on your own computer. Best for: any device, even a Raspberry Pi 5 or old laptop. Part of TC Mini: also runs in your phone's browser โ€” https://truthprotectors.github.io/TC-Mini/app/ ยท code https://github.com/truthprotectors/TC-Mini ยท all sizes https://huggingface.co/truthcoder/TC-Mini

ollama run hf.co/truthcoder/TC-Mini-0.6B-GGUF:Q4_K_M
llama-cli -hf truthcoder/TC-Mini-0.6B-GGUF:Q4_K_M

LM Studio: search truthcoder/TC-Mini-0.6B-GGUF. Add /no_think to a message to skip the thinking step.

File Quant Size
TC-Mini-0.6B-F16.gguf F16 1.20 GB
TC-Mini-0.6B-Q4_K_M.gguf Q4_K_M 0.40 GB
TC-Mini-0.6B-Q8_0.gguf Q8_0 0.64 GB

Q4_K_M = smallest, recommended ยท Q8_0 = near-lossless ยท F16 = full precision (for re-quantizing).

Lineage (honest): mlabonne/Qwen3-0.6B-abliterated (Qwen3 with refusal directions removed by mlabonne), converted with llama.cpp convert_hf_to_gguf.py and quantized with llama-quantize. Not fine-tuned by us. 0/8 refusals on our 8-prompt probe (browser build of the same weights). You are responsible for how you use it.

SHA-256:

334ed6f8e7df4cdcf6328d503873b0a409522845b3872f3d5b7b6b4f27b03073  TC-Mini-0.6B-F16.gguf
e2f58e2763f6a0394cf39ff2b4f3faaae443c73fc64fd50689f66bf90ce8b110  TC-Mini-0.6B-Q4_K_M.gguf
7afcfb1d156a41d1ecc32d8b409998d4e561231392aa3f263514248a5e098a24  TC-Mini-0.6B-Q8_0.gguf

License: Apache-2.0 (Qwen3).

Downloads last month
164
GGUF
Model size
0.6B params
Architecture
qwen3
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for truthcoder/TC-Mini-0.6B-GGUF

Finetuned
Qwen/Qwen3-0.6B
Quantized
(6)
this model