Skip to content
AI Atlas
ModelActiveOpen weightsIdentity probable

Granite 4.2 8B

IBMfamily · Granite 4.2huggingface.co/ibm-granite/granite-4.2-8b

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

Open in Graph
data quality72

Updated 1 h ago · first seen 11 Sept 2026

model_01M294WVPM426KEABXVAJ6F2H4

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 · 1 third-partySeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
1
API aliases
granite-4-2-8bibm-granite/granite-4.2-8bIdentifiers 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 weightsweights 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)

dimensions marked null are unknown, not false

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 7 d agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 7 d 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

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 7 d agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 7 d agomedium

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium

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=v4.0 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv4.0reasoningonconditions differ across rows → partially comparable2non-primary groupobs. 15 Sept 2026artificialanalysis.aiT2
Terminal-Benchagentic · accuracy · variant=v2.1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv2.1reasoningonconditions differ across rows → partially comparable2non-primary groupobs. 15 Sept 2026artificialanalysis.aiT2
SciCodecoding · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−31.6 ptvs Claude Fable 5.1obs. 18 Sept 2026artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningonversion4.3conditions differ across rows → partially comparable2−41.6vs Claude Fable 5.1obs. 18 Sept 2026artificialanalysis.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−49.5 ptvs Claude Fable 5.1obs. 18 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantDiamondreasoningonconditions differ across rows → partially comparable1non-primary groupobs. 18 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamond1−33.1 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. 12 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 →

Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MStatusObservedSource
OpenRoutercheapest outputibm-granite/granite-4.2-8b131.1Kout 118K$0.015active2 h agosince 11 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 1 provider

Output price history of Granite 4.2 8B$0$0.10$0.20$0.30Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.25 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $0.2511 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of Granite 4.2 8B$0$0.02$0.04$0.06$0.08Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.06 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $0.0611 Sept 2026

Hardware fit37

Estimated

37 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit5.6 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit5.6 GB est.Yes
Apple M2 Ultra4bit5.6 GB est.Yes
Apple M1 Ultra4bit5.6 GB est.Yes
Apple M3 Max4bit5.6 GB est.Yes
Apple M4 Max4bit5.6 GB est.Yes
Mac Studio (Apple M5 Max)4bit5.6 GB est.Yes
MacBook Pro (Apple M5 Max)4bit5.6 GB est.Yes
Apple M2 Max4bit5.6 GB est.Yes
Apple M1 Max4bit5.6 GB est.Yes
Apple M4 Pro4bit5.6 GB est.Yes
Mac mini (Apple M5 Pro)4bit5.6 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit5.6 GB est.Yes
Apple M3 Pro4bit5.6 GB est.Yes
Apple M1 Pro4bit5.6 GB est.Yes
Apple M2 Pro4bit5.6 GB est.Yes
Apple M44bit5.6 GB est.Yes
iMac (Apple M4)4bit5.6 GB est.Yes
Mac mini (Apple M6)4bit5.6 GB est.Yes
MacBook Air (Apple M5)4bit5.6 GB est.Yes
MacBook Pro (Apple M5)4bit5.6 GB est.Yes
Apple M24bit5.6 GB est.Yes
Apple M34bit5.6 GB est.Yes
Apple M14bit5.6 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB5.6 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB5.6 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB5.6 GB est.Yes
NVIDIA A100 80GB4bit80 GB5.6 GB est.Yes
NVIDIA H100 SXM4bit80 GB5.6 GB est.Yes
NVIDIA H100 NVL4bit94 GB5.6 GB est.Yes
NVIDIA DGX Spark4bit128 GB5.6 GB est.Yes
NVIDIA H2004bit141 GB5.6 GB est.Yes
NVIDIA H200 NVL4bit141 GB5.6 GB est.Yes
NVIDIA B2004bit180 GB5.6 GB est.Yes
AMD Instinct MI300X4bit192 GB5.6 GB est.Yes
AMD Instinct MI325X4bit256 GB5.6 GB est.Yes
NVIDIA DGX B2004bit1,440 GB5.6 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.
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
ANCESTORS 1DESCENDANTS 0 · ARTIFACTSgranite-4.1-8b-baseIBMgranite-4.1-8b-base — IBM1 quantizationartifacts · collapsed1 quantization — artifacts · collapsedGranite 4.2 8B8.79B params · this modelGranite 4.2 8B — 8.79B params · this model

Versions & Artifacts1

Version history

Context windowfirst observation only

11 Sept 2026current

Licensefirst observation only

17 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Opennessfirst observation only

11 Sept 2026current

Parametersfirst observation only

17 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

Change history51

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 17 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 17 Sept 2026 39 claims in force

Release date
7 Aug 2026
Openness
open-weights
License
Apache-2.0
Architecture
GraniteForCausalLM
Parameters
8.79B
Context window
131.1K tokens
Max output
118K tokens
Modalities
text
Input modalities
text
Output modalities
text
Languages
ar, cs, de, en, es, fr, it, ja, ko, nl, pt, zh
Base model
ibm-granite/granite-4.1-8b-base
File size
17.6 GB
Hugging Face repo
ibm-granite/granite-4.2-8b
Pipeline tag
text-generation
Downloads
78,150
Likes
79
Aa context window
131,072
Aa openness
open-weights
Access
open
Hf inference providers
deepinfra
Last modified
2026-09-04T21:02:25+00:00
Library name
transformers
License key
Apache-2.0
License raw
apache-2.0
Aa median output tokens per second
80.8
Downloads all time
78,266
Model type
granite
Openrouter id
ibm-granite/granite-4.2-8b
Openrouter listed at
31 Aug 2026
Reasoning
Yes
Structured output
Yes
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Tags
ar, cs, de, en, es, fr, granite, granite-4.2, ibm, it, ja, ko, nl, pt, reasoning, safetensors, text-generation, thinking, tool-calling, transformers, zh
Tool calling
Yes
Weights available
Yes
Weights dtype
BF16
51 claims · 39 properties

Release daterelease_date2

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
7 Aug 2026currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
31 Aug 2026supersededOpenRouter public model & pricing listingT2mediumdeterministic

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weightscurrentcurrentArtificial AnalysisT2mediumdeterministic

Licenselicense1

Claim history for License
ValueValid from → toStatusSourceConfidenceExtractor
Apache-2.0currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Architecturearchitecture1

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

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
8.79BcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Context windowcontext_length1

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

Max outputmax_output_tokens1

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

Modalitiesmodalities1

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

Input modalitiesmodalities_input1

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

Output modalitiesmodalities_output1

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

Languageslanguages1

Claim history for Languages
ValueValid from → toStatusSourceConfidenceExtractor
ar, cs, de, en, es, fr, it, ja, ko, nl, pt, zhcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Base modelbase_model1

Claim history for Base model
ValueValid from → toStatusSourceConfidenceExtractor
ibm-granite/granite-4.1-8b-basecurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

File sizefile_size_gb1

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

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
ibm-granite/granite-4.2-8bcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Pipeline tagpipeline_tag1

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

Model cardmodel_card_url1

Claim history for Model card
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/ibm-granite/granite-4.2-8bcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
78,150currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes2

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
79currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
78supersededHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Aa context windowaa_context_window1

Claim history for Aa context window
ValueValid from → toStatusSourceConfidenceExtractor
131,072 tokenscurrentcurrentArtificial AnalysisT2mediumdeterministic

Aa opennessaa_openness1

Claim history for Aa openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weightscurrentcurrentArtificial AnalysisT2mediumdeterministic

Accessaccess1

Claim history for Access
ValueValid from → toStatusSourceConfidenceExtractor
opencurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Hf inference providershf_inference_providers1

Claim history for Hf inference providers
ValueValid from → toStatusSourceConfidenceExtractor
deepinfracurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2026-09-04T21:02:25+00:00currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Library namelibrary_name1

Claim history for Library name
ValueValid from → toStatusSourceConfidenceExtractor
transformerscurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

License keylicense_key1

Claim history for License key
ValueValid from → toStatusSourceConfidenceExtractor
Apache-2.0currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

License rawlicense_raw1

Claim history for License raw
ValueValid from → toStatusSourceConfidenceExtractor
apache-2.0currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Aa median output tokens per secondmetric.aa_median_output_tokens_per_second11

Claim history for Aa median output tokens per second
ValueValid from → toStatusSourceConfidenceExtractor
91.6currentcurrentArtificial AnalysisT2mediumdeterministic
80.8supersededArtificial AnalysisT2mediumdeterministic
90.8supersededArtificial AnalysisT2mediumdeterministic
67.1supersededArtificial AnalysisT2mediumdeterministic
65.9supersededArtificial AnalysisT2mediumdeterministic
70.1supersededArtificial AnalysisT2mediumdeterministic
75.9supersededArtificial AnalysisT2mediumdeterministic
83.1supersededArtificial AnalysisT2mediumdeterministic
85.2supersededArtificial AnalysisT2mediumdeterministic
84supersededArtificial AnalysisT2mediumdeterministic
89.3supersededArtificial AnalysisT2mediumdeterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
ValueValid from → toStatusSourceConfidenceExtractor
78,266currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

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

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
ibm-granite/granite-4.2-8bcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter listed atopenrouter_listed_at1

Claim history for Openrouter listed at
ValueValid from → toStatusSourceConfidenceExtractor
31 Aug 2026currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Reasoningreasoning1

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
YescurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Structured outputstructured_output1

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

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_pcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
ar, cs, de, en, es, fr, granite, granite-4.2, ibm, it, ja, ko, nl, pt, reasoning, safetensors, text-generation, thinking, tool-calling, transformers, zhcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
YescurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Weights availableweights_available1

Claim history for Weights available
ValueValid from → toStatusSourceConfidenceExtractor
YescurrentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived

Weights dtypeweights_dtype1

Claim history for Weights dtype
ValueValid from → toStatusSourceConfidenceExtractor
BF16currentcurrentHugging 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

43

Source tiers

T243

Freshest observation

1 h ago

Conflicts

None

Source documents 6

Source documents
SourceDocumentTypeTierLast observedSnapshots
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=ibm-granite&p=0&sort=downloads listingT2· Quality secondary51 min ago41
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 h ago100
Hugging Face Hub (public pages, model cards, papers)huggingface.co/ibm-granite/granite-4.2-8b/raw/main/README.md model_cardT2· Quality secondary4 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/ibm-granite/granite-4.2-8b model_pageT2· Quality secondary5 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/ibm-granite/granite-4.2-8b-GGUF model_pageT2· Quality secondary5 h ago38
Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary6 h ago23

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

Data quality (72/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →