Skip to content
AI Atlas
ModelActive

Mistral-Medium-3.5-128B

Mistral AIhuggingface.co/mistralai/Mistral-Medium-3.5-128B

Open in Graph
data quality53

Updated 6 h ago · first seen 11 Sept 2026

model_01M294ZAR72W0HAPX2XE3R17EP

Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Hugging Face repo

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Capabilities

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.

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Hardware fit37

Estimated

19 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—73.9 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—73.9 GB est.Yes
Apple M2 Ultra4bit—73.9 GB est.Yes
Apple M1 Ultra4bit—73.9 GB est.Yes
Apple M3 Max4bit—73.9 GB est.Yes
Apple M4 Max4bit—73.9 GB est.Yes
Mac Studio (Apple M5 Max)4bit—73.9 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—73.9 GB est.Yes
Apple M2 Max4bit—73.9 GB est.Yes
NVIDIA A100 80GB4bit80 GB73.9 GB est.Yes
NVIDIA H100 SXM4bit80 GB73.9 GB est.Yes
NVIDIA H100 NVL4bit94 GB73.9 GB est.Yes
NVIDIA DGX Spark4bit128 GB73.9 GB est.Yes
NVIDIA H2004bit141 GB73.9 GB est.Yes
NVIDIA H200 NVL4bit141 GB73.9 GB est.Yes
NVIDIA B2004bit180 GB73.9 GB est.Yes
AMD Instinct MI300X4bit192 GB73.9 GB est.Yes
AMD Instinct MI325X4bit256 GB73.9 GB est.Yes
NVIDIA DGX B2004bit1,440 GB73.9 GB est.Yes
Apple M1 Max4bit—73.9 GB est.No
Apple M4 Pro4bit—73.9 GB est.No
Mac mini (Apple M5 Pro)4bit—73.9 GB est.No
MacBook Pro (Apple M5 Pro)4bit—73.9 GB est.No
Apple M3 Pro4bit—73.9 GB est.No
Apple M1 Pro4bit—73.9 GB est.No
Apple M2 Pro4bit—73.9 GB est.No
Apple M44bit—73.9 GB est.No
iMac (Apple M4)4bit—73.9 GB est.No
Mac mini (Apple M6)4bit—73.9 GB est.No
MacBook Air (Apple M5)4bit—73.9 GB est.No
MacBook Pro (Apple M5)4bit—73.9 GB est.No
Apple M24bit—73.9 GB est.No
Apple M34bit—73.9 GB est.No
Apple M14bit—73.9 GB est.No
NVIDIA GeForce RTX 30904bit24 GB73.9 GB est.No
NVIDIA GeForce RTX 40904bit24 GB73.9 GB est.No
NVIDIA GeForce RTX 50904bit32 GB73.9 GB est.No
Assumptions (6)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache approximated at 0.5 GB per 8 192 tokens of context, independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).

Timeline1

Full timeline →

Change history19

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 12 Sept 2026 20 claims in force

Release date
31 Mar 2026
Openness
open-weights
License
Other
Architecture
Mistral3ForConditionalGeneration
Parameters
127.7B
Languages
en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa, id, ms, ne, pl, ro, sr, sv, tr, uk, vi, hi, bn
Quantization format
fp8
File size
133.6 GB
Hugging Face repo
mistralai/Mistral-Medium-3.5-128B
Downloads
145,108
Likes
439
Gated
No
Is quantized
Yes
Last modified
2026-07-15T12:23:17+00:00
Downloads all time
1,027,252
Model type
mistral3
Tags
safetensors, mistral3, vLLM, en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa, id, ms, ne, pl, ro, sr, sv, tr, uk, vi, hi, bn, fp8
Weights available
Yes
Weights dtype
BF16, F8_E4M3
19 claims · 19 properties

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
31 Mar 2026 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weights → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Licenselicense1

Claim history for License
ValueValid from → toStatusSourceConfidenceExtractor
other → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
Mistral3ForConditionalGeneration → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
127.7B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Languageslanguages1

Claim history for Languages
ValueValid from → toStatusSourceConfidenceExtractor
en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa, id, ms, ne, pl, ro, sr, sv, tr, uk, vi, hi, bn → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Quantization formatquant_format1

Claim history for Quantization format
ValueValid from → toStatusSourceConfidenceExtractor
fp8 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

File sizefile_size_gb1

Claim history for File size
ValueValid from → toStatusSourceConfidenceExtractor
133.6 GB → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
mistralai/Mistral-Medium-3.5-128B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model cardmodel_card_url1

Claim history for Model card
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/mistralai/Mistral-Medium-3.5-128B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
145,108 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes1

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
438 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Gatedgated1

Claim history for Gated
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Is quantizedis_quantized1

Claim history for Is quantized
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2026-07-15T12:23:17+00:00 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
ValueValid from → toStatusSourceConfidenceExtractor
1,027,252 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
mistral3 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
safetensors, mistral3, vLLM, en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa, id, ms, ne, pl, ro, sr, sv, tr, uk, vi, hi, bn, fp8 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Weights dtypeweights_dtype1

Claim history for Weights dtype
ValueValid from → toStatusSourceConfidenceExtractor
BF16, F8_E4M3 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

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 →

Provenance

Attributed facts

19

Source tiers

T219

Freshest observation

6 h ago

Conflicts

None

Source documents 3

Source documents
SourceDocumentTypeTierLast observedSnapshots
Hugging Face Hub (public pages, model cards, papers)huggingface.co/mistralai/Mistral-Medium-3.5-128B/raw/main/README.md model_cardT2· Quality secondary5 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/mistralai/Mistral-Medium-3.5-128B model_pageT2· Quality secondary6 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=mistralai&p=0&sort=downloads listingT2· Quality secondary6 h ago6

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

Data quality (53/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →