---
license: apache-2.0
datasets:
- simplescaling/s1K-1.1
- nvidia/OpenMathReasoning
- mlabonne/FineTome-100k
language:
- en
library_name: transformers
base_model: prithivMLmods/Crux-Qwen3_OpenThinking-4B
pipeline_tag: text-generation
tags:
- text-generation-inference
- math
- sft
- code
- llama-cpp
- gguf-my-repo
---

# Triangle104/Crux-Qwen3_OpenThinking-4B-Q4_K_M-GGUF
This model was converted to GGUF format from [`prithivMLmods/Crux-Qwen3_OpenThinking-4B`](https://huggingface.co/prithivMLmods/Crux-Qwen3_OpenThinking-4B) 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/prithivMLmods/Crux-Qwen3_OpenThinking-4B) for more details on the model.

---
Crux-Qwen3_OpenThinking-4B is fine-tuned on the Qwen3-4B architecture, optimized for advanced open thinking, mathematical reasoning, and logical problem solving. This model is trained on the traces of sk1.1, which include 1,000 entries from the Gemini thinking trajectory, combined with fine-tuning on 100k tokens of open math reasoning
 data. This makes it highly effective for nuanced reasoning, educational
 tasks, and complex problem-solving requiring clear thought processes.

---
## 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/Crux-Qwen3_OpenThinking-4B-Q4_K_M-GGUF --hf-file crux-qwen3_openthinking-4b-q4_k_m.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Triangle104/Crux-Qwen3_OpenThinking-4B-Q4_K_M-GGUF --hf-file crux-qwen3_openthinking-4b-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/Crux-Qwen3_OpenThinking-4B-Q4_K_M-GGUF --hf-file crux-qwen3_openthinking-4b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Triangle104/Crux-Qwen3_OpenThinking-4B-Q4_K_M-GGUF --hf-file crux-qwen3_openthinking-4b-q4_k_m.gguf -c 2048
```