MI

Ministral 3 3B Reasoning 2512 Heretic

MistralGGUF by coder3101Updated 2026-01-18
Download on Hugging Face
Parameters3.43B
Context256K
Layers26
Architecturemistral3
Smallest quant2.1 GB
Quick answer

Ministral 3 3B Reasoning 2512 Heretic needs about 3.5 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 2.1 GB (Q4_K_M) to 6.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.

Ministral 3 3B Reasoning 2512 Heretic – a compact vision‑language model

Ministral 3 3B Reasoning 2512 Heretic is a 3.43 billion‑parameter model with a 256k context window. It supports vision, multilingual text, coding, reasoning, and tool calling. The model is edge‑optimized and licensed under Apache 2.0.

Good at

  • Vision‑enabled reasoning
  • Multilingual coding
  • Tool‑aware agentic tasks

Limits

  • Requires mmproj file for vision
  • Large context window may need more VRAM
  • No dedicated vision quant available

Best for

  • Lightweight reasoning agents
  • Multilingual code generation
  • Vision‑based question answering

Who it’s for. Developers needing a small, versatile vision‑language model for edge deployment. The model fits in 16 GB VRAM in BF16 and less than 8 GB when quantized, making it suitable for local inference on modest hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.1 GB 3.5 GB
Fits Get file →
Q5_K_M2.5 GB 3.8 GB
Fits Get file →
Q8_03.7 GB 5.0 GB
Fits Get file →
BF166.9 GB 8.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.15 GB file, ~3.5 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (2.47 GB file, ~3.8 GB memory). For 16 GB VRAM, BF16 (6.87 GB file, ~8.2 GB memory).

What GPU do you need for Ministral 3 3B Reasoning 2512 Heretic?

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 Q5_K_M (2.5 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (6.9 GB file, about 8.2 GB in use).

Which Ministral 3 3B Reasoning 2512 Heretic quant should you choose?

Q4_K_M is the usual starting point for Ministral 3 3B Reasoning 2512 Heretic: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemistral3
Parameters3.43B
Layers26
Trained context262,144 tokens
KV cache (fp16)104 KB per token

Source

Quantized bycoder3101
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,093
Last updated2026-01-18

Frequently asked questions about Ministral 3 3B Reasoning 2512 Heretic

How much VRAM does Ministral 3 3B Reasoning 2512 Heretic need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.1 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 3B Reasoning 2512 Heretic on an 8 GB GPU?

Yes, with Q8_0: the 3.7 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ministral 3 3B Reasoning 2512 Heretic GGUF?

It depends on the quant: Q4_K_M is 2.1 GB, Q5_K_M is 2.5 GB, Q8_0 is 3.7 GB, BF16 is 6.9 GB.

What context length does Ministral 3 3B Reasoning 2512 Heretic support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.

Where can I download Ministral 3 3B Reasoning 2512 Heretic GGUF?

The files are on Hugging Face in the coder3101/Ministral-3-3B-Reasoning-2512-heretic-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 3B Reasoning 2512 Heretic 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, using the Q4_K_M quantization which requires about 3.5 GB of VRAM at 8k context.

Do I need a separate mmproj file for vision?

Yes, download the 811 MB mmproj file to enable vision inputs.

Is the model licensed for commercial use?

It is released under Apache 2.0, allowing commercial and non‑commercial use.

Similar models

Browse all →

More from coder3101

All by coder3101 →

More Mistral models

All Mistral →

Other tiny models

All tiny models →