Model Intelligence Sheet
SOMEHOTMEAL/Ministral-3-14B-Janus-Abliterated-V2-Base_And_GGUF overview
base model: mistralai/Ministral 3 14B Instruct 2512 jenerallee78/Ministral 3 14B abliterated library name: transformers tags: mergekit merge Ministral 3 14B Ja…
Runs locally from ~4.89 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
5 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Ministral-3-14B-Janus-Abliterated-V2-Q2_K-GGUF.gguf | GGUF | Q2_K | 4.89 GB | Download |
| Ministral-3-14B-Janus-Abliterated-V2-Q4_K_M-GGUF.gguf | GGUF | Q4_K_M | 7.67 GB | Download |
| Ministral-3-14B-Janus-Abliterated-V2-Q6_K-GGUF.gguf | GGUF | Q6_K | 10.33 GB | Download |
| Ministral-3-14B-Janus-Abliterated-V2-Q8_0-GGUF.gguf | GGUF | Q8_0 | 13.37 GB | Download |
| Ministral-3-14B-Janus-Abliterated-V2-f16-GGUF.gguf | GGUF | F16 | 25.17 GB | Download |
Model Details
| Model ID | SOMEHOTMEAL/Ministral-3-14B-Janus-Abliterated-V2-Base_And_GGUF |
|---|---|
| Author | SOMEHOTMEAL |
| Pipeline | image-text-to-text |
| License | — |
| Base model | mistralai/Ministral-3-14B-Instruct-2512,jenerallee78/Ministral-3-14B-abliterated |
| Last modified | 2026-09-13T16:48:30.000Z |
Model README
---
base_model:
- mistralai/Ministral-3-14B-Instruct-2512
- jenerallee78/Ministral-3-14B-abliterated
library_name: transformers
tags:
- mergekit
- merge
---
Ministral-3-14B-Janus-Abliterated-V2
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Linear DARE merge method using mistralai/Ministral-3-14B-Instruct-2512 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
merge_method: dare_linear
base_model: mistralai/Ministral-3-14B-Instruct-2512
models:
- model: jenerallee78/Ministral-3-14B-abliterated
parameters:
weight: 0.60
density: 0.70
dtype: bfloat16
tokenizer_source: baseRun SOMEHOTMEAL/Ministral-3-14B-Janus-Abliterated-V2-Base_And_GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models