--- license: apache-2.0 base_model: mlabonne/Qwen3-1.7B-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 1.7B — GGUF (Ollama · LM Studio · llama.cpp) Private AI that runs fully on your own computer. Best for: small laptops, mini-PCs, phones. 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 ```bash ollama run hf.co/truthcoder/TC-Mini-1.7B-GGUF:Q4_K_M llama-cli -hf truthcoder/TC-Mini-1.7B-GGUF:Q4_K_M ``` LM Studio: search `truthcoder/TC-Mini-1.7B-GGUF`. Add `/no_think` to a message to skip the thinking step. | File | Quant | Size | |---|---|---| | `TC-Mini-1.7B-F16.gguf` | F16 | 3.45 GB | | `TC-Mini-1.7B-Q4_K_M.gguf` | Q4_K_M | 1.11 GB | | `TC-Mini-1.7B-Q8_0.gguf` | Q8_0 | 1.83 GB | Q4_K_M = smallest, recommended · Q8_0 = near-lossless · F16 = full precision (for re-quantizing). **Lineage (honest):** [mlabonne/Qwen3-1.7B-abliterated](https://huggingface.co/mlabonne/Qwen3-1.7B-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: ``` 1b35de4c0cb050e1ee70c02587b006189f07de4da9789f51cb6091c8a10f4f7a TC-Mini-1.7B-F16.gguf bdba0468be80603ded29033266e3c9343ac34989334d55a11583ef461e7f6432 TC-Mini-1.7B-Q4_K_M.gguf 21aa20dfb295589ba2ced06b6aceec5408533fe20887fd68835044572344f44f TC-Mini-1.7B-Q8_0.gguf ``` License: Apache-2.0 (Qwen3).