Skip to content
AI Atlas
ModelActive

Llama 3.2 3B Instruct

Meta AIhuggingface.co/meta-llama/Llama-3.2-3B-Instruct

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

Open in Graph
data quality65

Updated 6 h ago · first seen 11 Sept 2026

model_01M294WWNJ3JRF3C1RTJQJGGE0

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 8 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Architecture

Architecture

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

Model type

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

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Weights dtype

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

File size

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

Library name

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

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    No

    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 13 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Languages

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

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Providers & Pricing1

All offers in the price terminal →
Current prices per 1M tokens
ProviderInput / 1MOutput / 1MCached inBatch in / outContextObservedSource
OpenRoutermeta-llama/llama-3.2-3b-instruct$0.05$0.33——131.1K6 h agoopenrouter.aiT2

USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.

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 1 provider

Output price history of Llama 3.2 3B Instruct$0$0.10$0.20$0.30$0.40Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.33 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $0.3311 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of Llama 3.2 3B Instruct$0$0.02$0.04$0.06Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.05 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $0.0511 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—2.4 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—2.4 GB est.Yes
Apple M2 Ultra4bit—2.4 GB est.Yes
Apple M1 Ultra4bit—2.4 GB est.Yes
Apple M3 Max4bit—2.4 GB est.Yes
Apple M4 Max4bit—2.4 GB est.Yes
Mac Studio (Apple M5 Max)4bit—2.4 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—2.4 GB est.Yes
Apple M2 Max4bit—2.4 GB est.Yes
Apple M1 Max4bit—2.4 GB est.Yes
Apple M4 Pro4bit—2.4 GB est.Yes
Mac mini (Apple M5 Pro)4bit—2.4 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—2.4 GB est.Yes
Apple M3 Pro4bit—2.4 GB est.Yes
Apple M1 Pro4bit—2.4 GB est.Yes
Apple M2 Pro4bit—2.4 GB est.Yes
Apple M44bit—2.4 GB est.Yes
iMac (Apple M4)4bit—2.4 GB est.Yes
Mac mini (Apple M6)4bit—2.4 GB est.Yes
MacBook Air (Apple M5)4bit—2.4 GB est.Yes
MacBook Pro (Apple M5)4bit—2.4 GB est.Yes
Apple M24bit—2.4 GB est.Yes
Apple M34bit—2.4 GB est.Yes
Apple M14bit—2.4 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB2.4 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB2.4 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB2.4 GB est.Yes
NVIDIA A100 80GB4bit80 GB2.4 GB est.Yes
NVIDIA H100 SXM4bit80 GB2.4 GB est.Yes
NVIDIA H100 NVL4bit94 GB2.4 GB est.Yes
NVIDIA DGX Spark4bit128 GB2.4 GB est.Yes
NVIDIA H2004bit141 GB2.4 GB est.Yes
NVIDIA H200 NVL4bit141 GB2.4 GB est.Yes
NVIDIA B2004bit180 GB2.4 GB est.Yes
AMD Instinct MI300X4bit192 GB2.4 GB est.Yes
AMD Instinct MI325X4bit256 GB2.4 GB est.Yes
NVIDIA DGX B2004bit1,440 GB2.4 GB est.Yes
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).

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
DESCENDANTS 143b-de-ft-research_release3.3B3b-de-ft-research_release — 3.3B3b-de-pretrain-research_relea…3.78B3b-de-pretrain-research_release — 3.78B3b-es_it-ft-research_release3.3B3b-es_it-ft-research_release — 3.3B3b-es_it-pretrain-research_re…3.78B3b-es_it-pretrain-research_release — 3.78B3b-fr-ft-research_release3.3B3b-fr-ft-research_release — 3.3B3b-fr-pretrain-research_relea…3.78B3b-fr-pretrain-research_release — 3.78B+8 more descendantsLlama 3.2 3B Instruct3.21B params · this modelLlama 3.2 3B Instruct — 3.21B params · this model

Papers2

Timeline4

Full timeline →

Change history23

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 1 Jan 2025 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Llama 3.2 3B Instruct was not yet in AI Atlas on 1 Jan 2025

First seen 11 Sept 2026. Nothing is inferred backwards: no attribute is shown for dates before the first observation.
23 claims · 22 properties

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
25 Sept 2024 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Opennessopenness1

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

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
3.21B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Context windowcontext_length1

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
131.1K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
118K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Knowledge cutoffknowledge_cutoff1

Claim history for Knowledge cutoff
ValueValid from → toStatusSourceConfidenceExtractor
Dec 2023 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tokenizertokenizer1

Claim history for Tokenizer
ValueValid from → toStatusSourceConfidenceExtractor
Llama3 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
meta-llama/Llama-3.2-3B-Instruct → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
ValueValid from → toStatusSourceConfidenceExtractor
text-generation → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model cardmodel_card_url1

Claim history for Model card
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
1,587,087 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes2

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
2,559 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
2,558 → supersededHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it... → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Instruct typeinstruct_type1

Claim history for Instruct type
ValueValid from → toStatusSourceConfidenceExtractor
llama3 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2024-10-24T15:07:29+00:00 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
meta-llama/llama-3.2-3b-instruct → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, seed, stop, structured_outputs, temperature, top_k, top_logprobs, top_p → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

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

34

Source tiers

T234

Freshest observation

6 h ago

Conflicts

None

Source documents 16

Source documents
SourceDocumentTypeTierLast observedSnapshots
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary6 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/meta-llama/Llama-3.2-3B-Instruct model_pageT2· Quality secondary7 h ago3
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-zh-pretrain-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-ko-pretrain-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-de-pretrain-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-zh-ft-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-fr-pretrain-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-ko-ft-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-es_it-pretrain-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-es_it-ft-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-fr-ft-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-de-ft-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/3b-hi-ft-research_release model_pageT2· Quality secondary7 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/orpheus-3b-0.1-pretrained model_pageT2· Quality secondary7 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/canopylabs/orpheus-3b-0.1-ft model_pageT2· Quality secondary7 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=meta-llama&p=0&sort=downloads listingT2· Quality secondary7 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 (65/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →