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,...
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 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)
dimensions marked null are unknown, not false
Key facts
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 h agomedium
- Model card
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
Benchmarks12
Compare with another model →Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric
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 →
Providers & Pricing1
All offers in the price terminal →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
Output price · USD / 1M tokens 1 provider
- OpenRouter
- OpenRouterfirst observed $0.2511 Sept 2026
Input price · USD / 1M tokens 1 provider
- OpenRouter
- OpenRouterfirst observed $0.0611 Sept 2026
Hardware fit37
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 →- ancestor: granite-4.1-8b-base
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
- ibm-granite/granite-4.2-8b-GGUFIBM · GGUF—
Timeline7
Full timeline →Granite 4.2 8B: release date changed from 2026-08-31 to 2026-08-07
Release date31 Aug 2026→7 Aug 2026huggingfaceGranite 4.2 8B scores 18.35% on Terminal-Bench
artificial_analysisGranite 4.2 8B scores 9.68% on Humanity's Last Exam
artificial_analysisGranite 4.2 8B scores 63.13% on GPQA Diamond
artificial_analysisGranite 4.2 8B scores 11.81 on Artificial Analysis Intelligence Index
artificial_analysis
Change history51
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
Release daterelease_date2
Opennessopenness1
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Context windowcontext_length1
Max outputmax_output_tokens1
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Languageslanguages1
Base modelbase_model1
File sizefile_size_gb1
Hugging Face repohf_repo1
Pipeline tagpipeline_tag1
Model cardmodel_card_url1
Downloadsmetric.downloads1
Likesmetric.likes2
Aa context windowaa_context_window1
Aa opennessaa_openness1
Accessaccess1
Descriptiondescription1
Hf inference providershf_inference_providers1
Last modifiedlast_modified1
Library namelibrary_name1
License keylicense_key1
License rawlicense_raw1
Aa median output tokens per secondmetric.aa_median_output_tokens_per_second11
Downloads all timemetric.downloads_all_time1
Model typemodel_type1
Openrouter idopenrouter_id1
Openrouter listed atopenrouter_listed_at1
Reasoningreasoning1
Structured outputstructured_output1
Supported parameterssupported_parameters1
Tool callingtool_calling1
Weights availableweights_available1
Weights dtypeweights_dtype1
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
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 →