TC-Mini-0.6B-GGUF / README.md
truthcoder's picture
TC Mini 0.6B GGUF: Q4_K_M, Q8_0, F16
430f4c0 verified
|
Raw History Blame Contribute Delete
1.82 kB
metadata
license: apache-2.0
base_model: mlabonne/Qwen3-0.6B-abliterated
base_model_relation: quantized
pipeline_tag: text-generation
tags:
  - gguf
  - llama.cpp
  - ollama
  - lm-studio
  - on-device
  - offline
  - private
  - abliterated
  - uncensored
  - qwen3

TC Mini 0.6B — GGUF (Ollama · LM Studio · 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 — https://truthprotectors.github.io/TC-Mini/app/ · code https://github.com/truthprotectors/TC-Mini · 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 · Q8_0 = near-lossless · 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).