Skip to content
AI Atlas
ModelDeprecatedRestricted weightsIdentity probable

Llama 3.1 8B

Meta AIfamily · Llama 3.1huggingface.co/meta-llama/Llama-3.1-8B

Open in Graph
data quality68

Updated 4 h ago · first seen 11 Sept 2026

model_01M294WZMKQR9S4MFVDA0BJK2A

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
1 quantization0 official · 0 third-partySeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
None recorded
API aliases
llama-3-1-instruct-8bllama-3.1-8b-instantIdentifiers 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

Restricted weights— weights downloadable under Llama-3.1-Community; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.

Weights downloadable, but the licence restricts commercial use, hosting, derivatives or field of use (community, research and RAIL licences).

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    Yes

  • Redistribution

    Yes

  • Derivatives

    Yes

Licence: Llama 3.1 Community License (community · stated as “llama3.1”)

dimensions marked null are unknown, not false

Key facts

Release date

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

Status

Source:Artificial AnalysisT2observed 13 h agomedium

Architecture

Architecture

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

Model type

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

Parameters

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

Weights dtype

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

File size

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

Library name

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

Pipeline tag

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

Hugging Face repo

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

Capabilities

Modalities

Modalities unavailable.

Capabilities

  • Tool calling

    Unavailable

  • Structured output

    Unavailable

  • Reasoning

    No

    Artificial Analysis · T2

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:Artificial AnalysisT2observed 13 h agomedium

Languages

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

Benchmarks14

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
Terminal-Benchagentic · accuracy · variant=hard · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvarianthardreasoningoffconditions differ across rows → partially comparable2−65.1 ptvs gpt-5.6-solobs. 12 Sept 2026artificialanalysis.aiT2
Terminal-Benchagentic · accuracy · variant=v2.1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv2.1reasoningoffconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · variant=Telecom · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantTelecomreasoningoffconditions differ across rows → partially comparable1non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysis1−82.8 ptvs Z.ai GLM 5.2obs. 11 Sept 2026artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningoffversion4.3conditions differ across rows → partially comparable2−46.4vs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
IFBenchinstruction-following · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningoffconditions differ across rows → partially comparable2−54.8 ptvs Grok 4.3obs. 12 Sept 2026artificialanalysis.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningoffconditions differ across rows → partially comparable2−53.8 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantDiamondreasoningoffconditions differ across rows → partially comparable1non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamond1−70.4 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 14 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Hardware fit37

Estimated

37 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—5.1 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—5.1 GB est.Yes
Apple M2 Ultra4bit—5.1 GB est.Yes
Apple M1 Ultra4bit—5.1 GB est.Yes
Apple M3 Max4bit—5.1 GB est.Yes
Apple M4 Max4bit—5.1 GB est.Yes
Mac Studio (Apple M5 Max)4bit—5.1 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—5.1 GB est.Yes
Apple M2 Max4bit—5.1 GB est.Yes
Apple M1 Max4bit—5.1 GB est.Yes
Apple M4 Pro4bit—5.1 GB est.Yes
Mac mini (Apple M5 Pro)4bit—5.1 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—5.1 GB est.Yes
Apple M3 Pro4bit—5.1 GB est.Yes
Apple M1 Pro4bit—5.1 GB est.Yes
Apple M2 Pro4bit—5.1 GB est.Yes
Apple M44bit—5.1 GB est.Yes
iMac (Apple M4)4bit—5.1 GB est.Yes
Mac mini (Apple M6)4bit—5.1 GB est.Yes
MacBook Air (Apple M5)4bit—5.1 GB est.Yes
MacBook Pro (Apple M5)4bit—5.1 GB est.Yes
Apple M24bit—5.1 GB est.Yes
Apple M34bit—5.1 GB est.Yes
Apple M14bit—5.1 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB5.1 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB5.1 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB5.1 GB est.Yes
NVIDIA A100 80GB4bit80 GB5.1 GB est.Yes
NVIDIA H100 SXM4bit80 GB5.1 GB est.Yes
NVIDIA H100 NVL4bit94 GB5.1 GB est.Yes
NVIDIA DGX Spark4bit128 GB5.1 GB est.Yes
NVIDIA H2004bit141 GB5.1 GB est.Yes
NVIDIA H200 NVL4bit141 GB5.1 GB est.Yes
NVIDIA B2004bit180 GB5.1 GB est.Yes
AMD Instinct MI300X4bit192 GB5.1 GB est.Yes
AMD Instinct MI325X4bit256 GB5.1 GB est.Yes
NVIDIA DGX B2004bit1,440 GB5.1 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.
DESCENDANTS 2 · ARTIFACTSHermes-3-Llama-3.1-8B8.03BHermes-3-Llama-3.1-8B — 8.03BLlama 3.1 8B Instruct8.03BLlama 3.1 8B Instruct — 8.03B1 quantizationartifacts · collapsed1 quantization — artifacts · collapsedLlama 3.1 8B8.03B params · this modelLlama 3.1 8B — 8.03B params · this model

Versions & Artifacts1

Version history

Openness2 changes

11 Sept 2026→11 Sept 2026→11 Sept 2026current

Context windowfirst observation only

11 Sept 2026current

Licensefirst observation only

11 Sept 2026current

Parametersfirst observation only

11 Sept 2026current

Statusfirst 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 1

quantization 1

Papers1

Timeline8

Full timeline →

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

Context windowcontext_length1

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
128K tokens → currentcurrentArtificial AnalysisT2mediumdeterministic

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

T1T22 / 32

Freshest observation

4 h ago

Conflicts

None

Source documents 7

Source documents
SourceDocumentTypeTierLast observedSnapshots
Groq — docs & pricingconsole.groq.com/docs/models model_docsT1· Official1 h ago5
Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary4 h ago2
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=meta-llama&p=0&sort=downloads listingT2· Quality secondary4 h ago7
Hugging Face Hub (public pages, model cards, papers)huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B-GGUF model_pageT2· Quality secondary8 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B model_pageT2· Quality secondary8 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/meta-llama/Llama-3.1-8B model_pageT2· Quality secondary8 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/meta-llama/Llama-3.1-8B-Instruct model_pageT2· Quality secondary8 h ago4

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 →