Skip to content
AI Atlas
ModelActiveOpen weightsIdentity probable

Mistral Nemo

Mistral AIfamily · Mistralhuggingface.co/mistralai/Mistral-Nemo-Instruct-2

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

Open in Graph
data quality68

Updated 5 h ago · first seen 11 Sept 2026

model_01M294WWPHYQSVPWTZCZKD408V

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
2
API aliases
mistralai/mistral-nemoIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Open weights— weights downloadable under Apache-2.0; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.

Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    Yes

  • Redistribution

    Yes

  • Derivatives

    Yes

Licence: Apache License 2.0 (permissive · SPDX Apache-2.0 · stated as “apache-2.0”)

dimensions marked null are unknown, not false

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Unavailable

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Providers & Pricing2

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MOutput / 1MStatusObservedSource
Mistral AI La Plateformecheapest outputmistralai/mistral-nemo131.1Kout 16.4Kactive6 h agosince 11 Sept 2026openrouter.aiT2
OpenRoutermistralai/mistral-nemo131.1Kout 16.4Kactive1 h agosince 12 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 2 providers

Output price history of Mistral Nemo$0$0.01$0.02$0.03$0.04Sept 26Sept 26Sept 26Sept 26Sept 26Mistral AI La Plateforme: first observed → $0.03 · 11 Sept 2026OpenRouter: first observed → $0.03 · 12 Sept 2026
  • Mistral AI La Plateforme
  • OpenRouter
  • OpenRouterfirst observed $0.0312 Sept 2026
  • Mistral AI La Plateformefirst observed $0.0311 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of Mistral Nemo$0$0.005$0.01$0.015$0.02$0.025Sept 26Sept 26Sept 26Sept 26Sept 26Mistral AI La Plateforme: first observed → $0.019 · 11 Sept 2026OpenRouter: first observed → $0.019 · 12 Sept 2026
  • Mistral AI La Plateforme
  • OpenRouter
  • OpenRouterfirst observed $0.01912 Sept 2026
  • Mistral AI La Plateformefirst observed $0.01911 Sept 2026

Hardware fit37

Estimated

37 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—7.5 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—7.5 GB est.Yes
Apple M2 Ultra4bit—7.5 GB est.Yes
Apple M1 Ultra4bit—7.5 GB est.Yes
Apple M3 Max4bit—7.5 GB est.Yes
Apple M4 Max4bit—7.5 GB est.Yes
Mac Studio (Apple M5 Max)4bit—7.5 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—7.5 GB est.Yes
Apple M2 Max4bit—7.5 GB est.Yes
Apple M1 Max4bit—7.5 GB est.Yes
Apple M4 Pro4bit—7.5 GB est.Yes
Mac mini (Apple M5 Pro)4bit—7.5 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—7.5 GB est.Yes
Apple M3 Pro4bit—7.5 GB est.Yes
Apple M1 Pro4bit—7.5 GB est.Yes
Apple M2 Pro4bit—7.5 GB est.Yes
Apple M44bit—7.5 GB est.Yes
iMac (Apple M4)4bit—7.5 GB est.Yes
Mac mini (Apple M6)4bit—7.5 GB est.Yes
MacBook Air (Apple M5)4bit—7.5 GB est.Yes
MacBook Pro (Apple M5)4bit—7.5 GB est.Yes
Apple M24bit—7.5 GB est.Yes
Apple M34bit—7.5 GB est.Yes
Apple M14bit—7.5 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB7.5 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB7.5 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB7.5 GB est.Yes
NVIDIA A100 80GB4bit80 GB7.5 GB est.Yes
NVIDIA H100 SXM4bit80 GB7.5 GB est.Yes
NVIDIA H100 NVL4bit94 GB7.5 GB est.Yes
NVIDIA DGX Spark4bit128 GB7.5 GB est.Yes
NVIDIA H2004bit141 GB7.5 GB est.Yes
NVIDIA H200 NVL4bit141 GB7.5 GB est.Yes
NVIDIA B2004bit180 GB7.5 GB est.Yes
AMD Instinct MI300X4bit192 GB7.5 GB est.Yes
AMD Instinct MI325X4bit256 GB7.5 GB est.Yes
NVIDIA DGX B2004bit1,440 GB7.5 GB est.Yes
Assumptions (7)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), 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).
  • Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
ANCESTORS 1Mistral-Nemo-Base-240712.3BMistral-Nemo-Base-2407 — 12.3BMistral Nemo12.3B params · this modelMistral Nemo — 12.3B params · this model

Versions & Artifacts0

Version history

Context windowfirst observation only

11 Sept 2026current

Knowledge cutofffirst observation only

11 Sept 2026current

Licensefirst observation only

11 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Opennessfirst observation only

11 Sept 2026current

Parametersfirst observation only

11 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline3

Full timeline →
  • Listed by providerModelMistral NemoMistral AI

    OpenRouter lists Mistral Nemo at $0.019 in / $0.03 out per 1M tokens

    openrouter
    openrouter.ai
  • Release date changedModelMistral NemoMistral AI

    Mistral Nemo: release date changed from 2024-07-17 to 2024-07-19

    Release date17 Jul 2024→19 Jul 2024openrouter
    openrouter.ai
  • Release date changedModelMistral NemoMistral AI

    Mistral Nemo: release date changed from 2024-07-19 to 2024-07-17

    Release date19 Jul 2024→17 Jul 2024huggingface
    huggingface.co

Change history

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
1 claims · 1 propertiesShow all properties

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
mistral → 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

38

Source tiers

T238

Freshest observation

5 h ago

Conflicts

None

Source documents 4

Source documents
SourceDocumentTypeTierLast observedSnapshots
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary1 h ago11
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=mistralai&p=0&sort=downloads listingT2· Quality secondary5 h ago7
Hugging Face Hub (public pages, model cards, papers)huggingface.co/mistralai/Mistral-Nemo-Instruct-2407/raw/main/README.md model_cardT2· Quality secondary8 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/mistralai/Mistral-Nemo-Instruct-2407 model_pageT2· Quality secondary9 h ago5

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

Data quality (68/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →