--- license: mit language: - en base_model: Ba2han/Qwen-3-14B-Gemini-v0.1 tags: - llama-cpp - gguf-my-repo --- # Triangle104/Qwen-3-14B-Gemini-v0.1-Q4_K_M-GGUF This model was converted to GGUF format from [`Ba2han/Qwen-3-14B-Gemini-v0.1`](https://huggingface.co/Ba2han/Qwen-3-14B-Gemini-v0.1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Ba2han/Qwen-3-14B-Gemini-v0.1) for more details on the model. --- Use "You are an assistant with reasoning capabilities." system message to trigger Gemini-style thinking. Training Dataset - The fine-tuning dataset consists of ~300 diverse examples, 160 of which are directly from Gemini 2.5 Pro. Model - Trained on unsloth version of Qwen3-14B (instruct). Keep in mind that it's slightly overfit since the training dataset was quite small. --- ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Triangle104/Qwen-3-14B-Gemini-v0.1-Q4_K_M-GGUF --hf-file qwen-3-14b-gemini-v0.1-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Qwen-3-14B-Gemini-v0.1-Q4_K_M-GGUF --hf-file qwen-3-14b-gemini-v0.1-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Triangle104/Qwen-3-14B-Gemini-v0.1-Q4_K_M-GGUF --hf-file qwen-3-14b-gemini-v0.1-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Qwen-3-14B-Gemini-v0.1-Q4_K_M-GGUF --hf-file qwen-3-14b-gemini-v0.1-q4_k_m.gguf -c 2048 ```