CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.mistral / Ministral-3-8B-Instruct-2512-BF16
From: mistralai <huggingface.co/mistralai>Newsgroups: alt.freeweights.mistralSubject:

Ministral-3-8B-Instruct-2512-BF16

Date: 2026-11-14Commit: f6fae97Signed: 2DC28CC7B26A283B ✓

Model with 8.9B parameters. Safetensors weights, 35.7 GB in all. Published by mistralai under Apache-2.0.

8.9B params35.7GBMinistral-3-8B-Instruct-2512-BF16safetensorspermissive
FactsParams8.9BSize35.7 GBFormatssafetensorsTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get mistralai/Ministral-3-8B-Instruct-2512-BF16
# manifest sha256 59a2e85bdfd2… · 35.7 GB · 18 files
$ fw verify ./Ministral-3-8B-Instruct-2512-BF16 mistralai/Ministral-3-8B-Instruct-2512-BF16
From sourceHosted (signed)mistralai/Ministral-3-8B-Instruct-2512-BF16Last check: 2026-11-14 21:24 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of Ministral-3-8B-Base-2512.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
35.7 GB
Weights
17.8 GB (safetensors)
Parameters
8.9B
Formats
safetensors
Task
not tagged
License
Apache-2.0 (permissive)
Files
18, each with a sha256
Publisher
mistralai
Added
2026-11-14
Section
alt.freeweights.mistral
Lineage

Original release from the publisher.

Base model: mistralai/Ministral-3-8B-Base-2512

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 21:24 UTCpassed

Model card

From the publisher at commit f6fae97. Shown as plain text with links; images open at the publisher.

Ministral 3 8B Instruct 2512 BF16#

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

This model is the instruct post-trained version, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 8B can even be deployed locally, capable of fitting in 24GB of VRAM in BF16, and less than 12GB of RAM/VRAM when quantized.

We provide a no-loss FP8 version here, you can find other formats and quantizations in the Ministral 3 - Additional Checkpoints collection.

Learn more in our blog post and paper.

Key Features#

Ministral 3 8B consists of two main architectural components:

  • 8.4B Language Model
  • 0.4B Vision Encoder

The Ministral 3 8B Instruct model offers the following capabilities:

  • Vision: Enables the model to analyze images and provide insights based on visual content, in addition to text.
  • Multilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.
  • System Prompt: Maintains strong adherence and support for system prompts.
  • Agentic: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
  • Edge-Optimized: Delivers best-in-class performance at a small scale, deployable anywhere.
  • Apache 2.0 License: Open-source license allowing usage and modification for both commercial and non-commercial purposes.
  • Large Context Window: Supports a 256k context window.
Use Cases#

Perfect for balanced performance in local or embedded systems, combining versatility with efficiency.

  • Chat interfaces in constrained environments
  • Local daily-driver AI assistant
  • Image/document description and understanding
  • Translation and content generation
  • Specialized agentic use cases
  • Fine-tuning and specialization
  • And more...

Bringing advanced AI capabilities to resource-constrained environments.

Ministral 3 Family#

Model NameTypePrecisionLink
Ministral 3 3B Base 2512Base pre-trainedBF16Hugging Face
Ministral 3 3B Instruct 2512Instruct post-trainedBF16Hugging Face
Ministral 3 3B Reasoning 2512Reasoning capableBF16Hugging Face
Ministral 3 8B Base 2512Base pre-trainedBF16Hugging Face
Ministral 3 8B Instruct 2512Instruct post-trainedBF16Hugging Face
Ministral 3 8B Reasoning 2512Reasoning capableBF16Hugging Face
Ministral 3 14B Base 2512Base pre-trainedBF16Hugging Face
Ministral 3 14B Instruct 2512Instruct post-trainedBF16Hugging Face
Ministral 3 14B Reasoning 2512Reasoning capableBF16Hugging Face

Other formats available here.

Benchmark Results#

We compare Ministral 3 to similar sized models.

Reasoning#
ModelAIME25AIME24GPQA DiamondLiveCodeBench
Ministral 3 14B0.8500.8980.7120.646
Qwen3-14B (Thinking)0.7370.8370.6630.593
Ministral 3 8B0.7870.8600.6680.616
Qwen3-VL-8B-Thinking0.7980.8600.6710.580
Ministral 3 3B0.7210.7750.5340.548
Qwen3-VL-4B-Thinking0.6970.7290.6010.513
Instruct#
ModelArena HardWildBenchMATH Maj@1MM MTBench
Ministral 3 14B0.55168.50.9048.49
Qwen3 14B (Non-Thinking)0.42765.10.870NOT MULTIMODAL
Gemma3-12B-Instruct0.43663.20.8546.70
Ministral 3 8B0.50966.80.8768.08
Qwen3-VL-8B-Instruct0.52866.30.9468.00
Ministral 3 3B0.30556.80.8307.83
Qwen3-VL-4B-Instruct0.43856.80.9008.01
Qwen3-VL-2B-Instruct0.16342.20.7866.36
Gemma3-4B-Instruct0.31849.10.7595.23
Base#
ModelMultilingual MMLUMATH CoT 2-ShotAGIEval 5-shotMMLU Redux 5-shotMMLU 5-shotTriviaQA 5-shot
Ministral 3 14B0.7420.6760.6480.8200.7940.749
Qwen3 14B Base0.7540.6200.6610.8370.8040.703
Gemma 3 12B Base0.6900.4870.5870.7660.7450.788
Ministral 3 8B0.7060.6260.5910.7930.7610.681
Qwen 3 8B Base0.7000.5760.5960.7940.7600.639
Ministral 3 3B0.6520.6010.5110.7350.7070.592
Qwen 3 4B Base0.6770.4050.5700.7590.7130.530
Gemma 3 4B Base0.5160.2940.4300.6260.5890.640

License#

This model is licensed under the Apache 2.0 License.

You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.

Files

18 files · 35.7 GBWeights 17.8 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 18 files with their sha256
FileSizesha256
.gitattributes1.62 KB07b3b4b04ce1da1f27be4f1ff90006c9b8ace80cc0eb81bdd182a11257f4498c
README.md8.64 KBf390689977775d8ee2196a56d469f77293a1a33400069a6a2a00c5dc95f53510
SYSTEM_PROMPT.txt2.41 KB66e0fda8c8ab269ccd010dca6196931d475a22c3f2eebe5b6b3a2ec33a354d0e
chat_template.jinja11.9 KB74eeb55fd3341286ec3fd44e902b7120721acc81cd394e96b431f85e93a1ea56
config.json1.58 KB3953b565385881fe1e80980fa8f797ffef5dbcc170851b5f90d60ddcb1905f58
consolidated.safetensors17.8 GB44db184fe2b0b08edea6370ad8403d7b17d604d38127133f50a3da111a874eca
generation_config.json131 Be0923390059f84a9180b00e5501778acc45ea9856cd7f2fd68208b360927c677
model-00001-of-00004.safetensors4.98 GB95f4da19c81e6a06d4f0c61cac3dfdd85ef463a7955473dc4c07e570fd2342f9
model-00002-of-00004.safetensors5.00 GB18275e4c8413d0ed4b0cb8380fe1fd4faeee34189960fdd92ef5b0d3f4ed1b98
model-00003-of-00004.safetensors4.92 GB980d1d3635ae29a6e629e2f7ad589c882eba270c3f66da74da4f8ccb11845687
model-00004-of-00004.safetensors2.94 GBfa80e52af465c5644b18b623eeeebb1d50e47dafbee73816bf26f2473f88d369
model.safetensors.index.json52.7 KB639a9c27a864b0be21e9e0fd1313f120d24c45563723797ebf611c6fce75b822
params.json1.10 KB81b8377f36c5b3d60900b333214d85160a0500b84576e969092c6fd214f69538
processor_config.json976 Bece2373c2ae391bce18785a1810543bc6173a1f28b6767cffab2c35dbea5f002
special_tokens_map.json147 KB0a5c981e8c5c6f8886ee007a6d4543a0be6b221cb9ca32a8709384a4c6fc8cbb
tekken.json16.8 MB600bb27946565481ecf51ba8aee252e49b9a68507866080ac9c30185bb312843
tokenizer.json17.1 MBd5f6046775b112f0e2d456ee9dba450684ab964fe5c4e231599bdc6773028135
tokenizer_config.json198 KBf59f7294e4f26383d0ea93840fe21cf197784be0842a8301a0343e8c34ed0d6d
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
f6fae97957 pinned now manifest updated, same commit2026-11-14 21:24 UTC18 files · 35.7 GB
f6fae979572026-11-14 21:24 UTC18 files · 35.7 GB

Use it

$ fw get mistralai/Ministral-3-8B-Instruct-2512-BF16
# manifest sha256 59a2e85bdfd2… · 35.7 GB · 18 files
$ fw verify ./Ministral-3-8B-Instruct-2512-BF16 mistralai/Ministral-3-8B-Instruct-2512-BF16
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mistralai/Ministral-3-8B-Instruct-2512-BF16.json --dir ./Ministral-3-8B-Instruct-2512-BF16 $ python3 fw.py verify ./Ministral-3-8B-Instruct-2512-BF16 ./mistralai__Ministral-3-8B-Instruct-2512-BF16.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mistralai/Ministral-3-8B-Instruct-2512-BF16 --revision f6fae9795746f63c9be8344932f01275f3c63734 --local-dir ./Ministral-3-8B-Instruct-2512-BF16
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
README.md
Text sha256
f390689977775d8ee2196a56d469f77293a1a33400069a6a2a00c5dc95f53510
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mistralai <huggingface.co/mistralai>Newsgroups: alt.freeweights.mistralSubject: Ministral-3-8B-Instruct-2512-BF16Date: 2026-11-14Commit: f6fae97Signed: 2DC28CC7B26A283B ✓
Upstream
mistralai/Ministral-3-8B-Instruct-2512-BF16
Pinned commit
f6fae9795746f63c9be8344932f01275f3c63734
Manifest
Ministral-3-8B-Instruct-2512-BF16.json · .minisig
Manifest sha256
59a2e85bdfd29bc05df4ba36ea81f36f239bf045071b2aa0dbffa900e40969e0
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:24 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mistralai/Ministral-3-8B-Instruct-2512-BF16.json $ curl -O https://freeweights.allternit.com/manifests/mistralai/Ministral-3-8B-Instruct-2512-BF16.json.minisig $ minisign -Vm Ministral-3-8B-Instruct-2512-BF16.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

mistralai/Ministral-3-8B-Base-2512 · this model is a finetune of it

3 models in the catalog name this one as their parent.

Quantizations
3
Quantizations 3
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mistralai/Ministral-3-8B-Instruct-2512-BF16
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Ministral-3-8B-Instruct-2512-BF16.json. Provenance. Takedown history: none.
Source
huggingface.co/mistralai/Ministral-3-8B-Instruct-2512-BF16

Variants

3 quantized or adapter builds of Ministral-3-8B-Instruct-2512-BF16. Each has its own license check and page.

SubjectSizeParamsLicenseDate
mistralai_Ministral-3-8B-Instruct-2512-GGUFHosted (signed) From: bartowski in alt.freeweights.mistral135 GB—Permissive2026-11-15Ministral-3-8B-Instruct-2512-GGUFHosted (signed) From: lmstudio-community in alt.freeweights.mistral22.1 GB—Permissive2026-11-15Ministral-3-8B-Instruct-2512-GGUFHosted (signed) From: ggml-org in alt.freeweights.mistral9.49 GB—Permissive2026-11-15

Related models

All of alt.freeweights.mistral →
From: bartowski <huggingface.co/bartowski>Subject: alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF
From: microsoft <huggingface.co/microsoft>Subject: chatbench-mistral-7b
From: NousResearch <huggingface.co/NousResearch>Subject: DeepHermes-3-Mistral-24B-Preview
From: mistralai <huggingface.co/mistralai>Subject: Devstral-Small-2-24B-Instruct-2512
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-4bit
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-6bit