MI

Ministral 3 14B Abliterated

MistralGGUF by mradermacherUpdated 2026-01-10
Download on Hugging Face
Parameters13.5B
Context256K
Layers40
Architecturemistral3
Smallest quant0.0 GB
Quick answer

Ministral 3 14B Abliterated needs about 10.1 GB of memory at Q4_K_M (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 11.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Ministral 3 14B Abliterated – an abliterated, uncensored LLM

Ministral 3 14B Abliterated is a 13.5B parameter model based on Mistral architecture. It has been abliterated to remove refusal behavior, enabling broader topic engagement. The model supports tools and is licensed under Apache 2.0.

Good at

  • Tool usage
  • Uncensored conversations
  • Large context handling

Limits

  • No vision support
  • Requires high VRAM for larger quants
  • No refusal behavior may lead to policy violations

Best for

  • Research on uncensored language models
  • Tool‑integrated chatbots
  • Educational demonstrations

Who it’s for. Researchers and developers needing an uncensored, tool‑aware LLM for experimentation. The model is suitable for academic projects and prototype chat applications where refusal behavior is undesirable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.8 GB
Fits Get file →
IQ1_S3.3 GB 5.1 GB
Fits Get file →
IQ1_M3.5 GB 5.3 GB
Fits Get file →
IQ2_XXS3.9 GB 5.8 GB
Fits Get file →
IQ2_XS4.3 GB 6.1 GB
Fits Get file →
IQ2_S4.5 GB 6.4 GB
Fits Get file →
IQ2_M4.8 GB 6.7 GB
Fits Get file →
Q2_K_S4.9 GB 6.8 GB
Fits Get file →
Q2_K5.2 GB 7.1 GB
Fits Get file →
IQ3_XXS5.4 GB 7.3 GB
Tight Get file →
IQ3_XS5.8 GB 7.7 GB
Tight Get file →
Q3_K_S6.1 GB 7.9 GB
Tight Get file →
IQ3_S6.1 GB 7.9 GB
Tight Get file →
IQ3_M6.3 GB 8.1 GB
Too big Get file →
Q3_K_M6.7 GB 8.5 GB
Too big Get file →
Q3_K_L7.2 GB 9.1 GB
Too big Get file →
IQ4_XS7.4 GB 9.3 GB
Too big Get file →
IQ4_NL7.8 GB 9.6 GB
Too big Get file →
Q4_07.8 GB 9.6 GB
Too big Get file →
Q4_K_S7.8 GB 9.7 GB
Too big Get file →
Q4_K_M8.2 GB 10.1 GB
Too big Get file →
Q4_18.6 GB 10.4 GB
Too big Get file →
Q5_K_S9.4 GB 11.2 GB
Too big Get file →
Q5_K_M9.6 GB 11.5 GB
Too big Get file →
Q6_K11.1 GB 12.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (3.25 GB, 5.1 GB memory) or IQ1_M (3.5 GB, 5.3 GB memory). With 12 GB VRAM, Q3_K_M (6.68 GB, 8.5 GB memory) or Q4_K_M (8.24 GB, 10.1 GB memory) are suitable. Larger VRAM allows higher‑quality quants such as Q5_K_M or Q6_K.

What GPU do you need for Ministral 3 14B Abliterated?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ2_XXS (3.9 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_S (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.6 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.1 GB file, about 12.9 GB in use).

Which Ministral 3 14B Abliterated quant should you choose?

Q4_K_M is the usual starting point for Ministral 3 14B Abliterated: it balances file size and quality well. Here it is a 8.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemistral3
Parameters13.5B
Layers40
Trained context262,144 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,020
Last updated2026-01-10

Frequently asked questions about Ministral 3 14B Abliterated

How much VRAM does Ministral 3 14B Abliterated need?

About 10.1 GB at Q4_K_M with an 8K context window. That is the 8.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Ministral 3 14B Abliterated on an 8 GB GPU?

Yes, with IQ3_S: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ministral 3 14B Abliterated GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.5 GB, IQ2_XXS is 3.9 GB, IQ2_XS is 4.3 GB, IQ2_S is 4.5 GB and 19 more.

What context length does Ministral 3 14B Abliterated support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Ministral 3 14B Abliterated GGUF?

The files are on Hugging Face in the mradermacher/Ministral-3-14B-abliterated-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Ministral 3 14B Abliterated use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quant files, which are 3.25 GB and 3.5 GB respectively and require about 5.1 GB and 5.3 GB of VRAM at 8 k context.

Does this model support vision?

No, it is a text‑only model; no vision files are provided.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of Ministral-3-14B-abliterated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other medium models

All medium models →