unsloth/deepseek-r1-distill-llama-8b-ggufvsunsloth/ministral-3-14b-instruct-2512-gguf
Side-by-side comparison of unsloth/deepseek-r1-distill-llama-8b-gguf and unsloth/ministral-3-14b-instruct-2512-gguf: downloads, license, context length, tasks, and benchmarks.
unsloth/deepseek-r1-distill-llama-8b-gguf
We have a free Google Colab notebook for turning Llama 3.1 (8B) into a reasoning model: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-GRPO.ipynb
unsloth/ministral-3-14b-instruct-2512-gguf
The largest model in the Ministral 3 family, **Ministral 3 14B** offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities. The Ministral 3 family is designed for edge…
Side-by-side Specifications
| unsloth/deepseek-r1-distill-llama-8b-gguf | unsloth/ministral-3-14b-instruct-2512-gguf | |
|---|---|---|
| Author | unsloth | unsloth |
| Pipeline Task | text-generation | — |
| Library | transformers | vllm |
| Downloads | 41,456 | 28,807 |
| Likes | 295 | 81 |
| License | Unknown | Unknown |
| Context Length | — | — |
| Created | 2025-01-20 | 2025-12-02 |
| Last Modified | 2025-05-10 | 2025-12-04 |
| Tags |
View full details: unsloth/deepseek-r1-distill-llama-8b-gguf · unsloth/ministral-3-14b-instruct-2512-gguf