bartowski/ministral-8b-instruct-2410-ggufvsunsloth/ministral-3-14b-instruct-2512-gguf
Side-by-side comparison of bartowski/ministral-8b-instruct-2410-gguf and unsloth/ministral-3-14b-instruct-2512-gguf: downloads, license, context length, tasks, and benchmarks.
bartowski/ministral-8b-instruct-2410-gguf
Using llama.cpp release b3930 for quantization. Original model: https://huggingface.co/mistralai/Ministral-8B-Instruct-2410 All quants made using imatrix option with dataset from here Run them in LM Studio
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
| bartowski/ministral-8b-instruct-2410-gguf | unsloth/ministral-3-14b-instruct-2512-gguf | |
|---|---|---|
| Author | bartowski | unsloth |
| Pipeline Task | text-generation | — |
| Library | — | vllm |
| Downloads | 22,664 | 28,807 |
| Likes | 56 | 81 |
| License | Unknown | Unknown |
| Context Length | — | — |
| Created | 2024-10-21 | 2025-12-02 |
| Last Modified | 2024-10-21 | 2025-12-04 |
| Tags |
View full details: bartowski/ministral-8b-instruct-2410-gguf · unsloth/ministral-3-14b-instruct-2512-gguf