Specification

Release date: 9 Dec 2025
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Openness: open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
License: apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Architecture: Mistral3ForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Parameters: 24B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Base model: mistralai/Devstral-Small-2-24B-Instruct-2512
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Quantization: 4bit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Quantization format: mlx
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
File size: 15.1 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Hugging Face repo: mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Pipeline tag: image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Model card: huggingface.co/mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Downloads: 98,941
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Likes: 8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Gated: No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Is quantized: Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Last modified: 2026-07-04T22:46:55+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Library name: mlx
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Downloads all time: 1,527,201
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Model type: mistral3
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Tags: mlx, safetensors, mistral3, mistral-common, 4-bit, image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
Weights dtype: BF16, U32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

22

Source tiers

T222

Freshest observation

1 h ago

Conflicts

None

Modalities

Modalities unavailable.

Capabilities

Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable

No capability flags have been observed from a source yet — we do not infer them.

No structured attributes yet.

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.

Current prices

No current prices recorded

Prices appear when a provider publishes a public pricing page we crawl.

Price history

Estimated

Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.

Estimated hardware fit
Hardware	Quantization	Memory	Est. need	Fits
NVIDIA DGX B200	4bit	1,440 GB	14.3 GB	Yes
Apple M3 Ultra	4bit	—	14.3 GB	Yes
Mac Studio (Apple M5 Ultra)	4bit	—	14.3 GB	Yes
AMD Instinct MI325X	4bit	256 GB	14.3 GB	Yes
AMD Instinct MI300X	4bit	192 GB	14.3 GB	Yes
Apple M2 Ultra	4bit	—	14.3 GB	Yes
NVIDIA B200	4bit	180 GB	14.3 GB	Yes
NVIDIA H200	4bit	141 GB	14.3 GB	Yes
NVIDIA H200 NVL	4bit	141 GB	14.3 GB	Yes
Apple M1 Ultra	4bit	—	14.3 GB	Yes
Apple M3 Max	4bit	—	14.3 GB	Yes
Apple M4 Max	4bit	—	14.3 GB	Yes
Mac Studio (Apple M5 Max)	4bit	—	14.3 GB	Yes
MacBook Pro (Apple M5 Max)	4bit	—	14.3 GB	Yes
NVIDIA DGX Spark	4bit	128 GB	14.3 GB	Yes
Apple M2 Max	4bit	—	14.3 GB	Yes
NVIDIA H100 NVL	4bit	94 GB	14.3 GB	Yes
NVIDIA A100 80GB	4bit	80 GB	14.3 GB	Yes
NVIDIA H100 SXM	4bit	80 GB	14.3 GB	Yes
Apple M1 Max	4bit	—	14.3 GB	Yes
Apple M4 Pro	4bit	—	14.3 GB	Yes
Mac mini (Apple M5 Pro)	4bit	—	14.3 GB	Yes
MacBook Pro (Apple M5 Pro)	4bit	—	14.3 GB	Yes
Apple M3 Pro	4bit	—	14.3 GB	Yes
Apple M1 Pro	4bit	—	14.3 GB	Yes
Apple M2 Pro	4bit	—	14.3 GB	Yes
Apple M4	4bit	—	14.3 GB	Yes
iMac (Apple M4)	4bit	—	14.3 GB	Yes
Mac mini (Apple M6)	4bit	—	14.3 GB	Yes
MacBook Air (Apple M5)	4bit	—	14.3 GB	Yes
MacBook Pro (Apple M5)	4bit	—	14.3 GB	Yes
NVIDIA GeForce RTX 5090	4bit	32 GB	14.3 GB	Yes
Apple M2	4bit	—	14.3 GB	Yes
Apple M3	4bit	—	14.3 GB	Yes
NVIDIA GeForce RTX 3090	4bit	24 GB	14.3 GB	Yes
NVIDIA GeForce RTX 4090	4bit	24 GB	14.3 GB	Yes
Apple M1	4bit	—	14.3 GB	No

Ancestors 2

Devstral-Small-2-24B-Instruct-251224B
Mistral-Small-3.1-24B-Base-2503Mistral AI

This model

mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit

24B params

Quantizations 0

None recorded.

Descendants 0

None recorded.

Papers 0

No papers linked yet.

Repositories 0

No repositories linked yet.

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

22 claims · 22 properties

Release daterelease_date1

Claim history for Release date
Value	Valid from → to	Status	Source	Confidence	Extractor
9 Dec 2025	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Opennessopenness1

Claim history for Openness
Value	Valid from → to	Status	Source	Confidence	Extractor
open-weights	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Licenselicense1

Claim history for License
Value	Valid from → to	Status	Source	Confidence	Extractor
apache-2.0	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Architecturearchitecture1

Claim history for Architecture
Value	Valid from → to	Status	Source	Confidence	Extractor
Mistral3ForConditionalGeneration	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Parametersparameter_count1

Claim history for Parameters
Value	Valid from → to	Status	Source	Confidence	Extractor
24B	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Base modelbase_model1

Claim history for Base model
Value	Valid from → to	Status	Source	Confidence	Extractor
mistralai/Devstral-Small-2-24B-Instruct-2512	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Quantizationquantization1

Claim history for Quantization
Value	Valid from → to	Status	Source	Confidence	Extractor
4bit	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Quantization formatquant_format1

Claim history for Quantization format
Value	Valid from → to	Status	Source	Confidence	Extractor
mlx	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

File sizefile_size_gb1

Claim history for File size
Value	Valid from → to	Status	Source	Confidence	Extractor
15.1 GB	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
Value	Valid from → to	Status	Source	Confidence	Extractor
mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
Value	Valid from → to	Status	Source	Confidence	Extractor
image-text-to-text	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Model cardmodel_card_url1

Claim history for Model card
Value	Valid from → to	Status	Source	Confidence	Extractor
https://huggingface.co/mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Downloadsmetric.downloads1

Claim history for Downloads
Value	Valid from → to	Status	Source	Confidence	Extractor
98,941	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Likesmetric.likes1

Claim history for Likes
Value	Valid from → to	Status	Source	Confidence	Extractor
8	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Gatedgated1

Claim history for Gated
Value	Valid from → to	Status	Source	Confidence	Extractor
No	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Is quantizedis_quantized1

Claim history for Is quantized
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Last modifiedlast_modified1

Claim history for Last modified
Value	Valid from → to	Status	Source	Confidence	Extractor
2026-07-04T22:46:55+00:00	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Library namelibrary_name1

Claim history for Library name
Value	Valid from → to	Status	Source	Confidence	Extractor
mlx	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
Value	Valid from → to	Status	Source	Confidence	Extractor
1,527,201	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Model typemodel_type1

Claim history for Model type
Value	Valid from → to	Status	Source	Confidence	Extractor
mistral3	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Tagstags1

Claim history for Tags
Value	Valid from → to	Status	Source	Confidence	Extractor
mlx, safetensors, mistral3, mistral-common, 4-bit, image-text-to-text	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Weights dtypeweights_dtype1

Claim history for Weights dtype
Value	Valid from → to	Status	Source	Confidence	Extractor
BF16, U32	11 Sept 2026 21:49 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New modelModelmlx-community/Devstral-Small-2-24B-Instruct-2512-4bitMLX Community
New model: mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit (MLX Community)
huggingface
huggingface.co

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit	model_page	T2· Quality secondary	1 h ago	3
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=mlx-community&p=0&sort=downloads	listing	T2· Quality secondary	2 h ago	3
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit/raw/main/README.md	model_card	T2· Quality secondary	2 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.