Skip to content
ModelCap

granite 3.3 2b instruct

Official publisher releaseOpen weights6.9d #312 → #307

IBM Granite·#307 of 352 on the current board

granite 3.3 2b instruct is a language model from IBM Granite. It ranks #307 of 352 on ModelCap's current board, with an Index score of 13.3, modeled from its measured predecessor. Its score range of 0.0–27.0 spans positions #252–#352. Its weights are openly downloadable.

Figures as of 6 Nov 2026, 20:49 UTC · download the public dataset · methodology

ModelCap Index · Current board
13.3#307
Modeled from its measured predecessor · range 0.0–27.0
Market Gravity
13.7Decreased by 0.6
Secondary market signal

OpenRouter endpoint status could not be refreshed. This model is not treated as currently served until a successful observation arrives.

Input
Self-hosted
weights only · no listed API price
Output
Self-hosted
weights only · no listed API price
Context
—
tokens
Providers
0
endpoints

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

Other versions (3)

ModelCap Index · Current board

Methodology
13.3
Modeled from its measured predecessor
Current board
#307 of 352
Score range
0.0–27.0
Rank range
#252–#352
Technical details
Public rank basis
Modeled · succession (architecture)
Evidence label
Modeled · succession · publisher-corpus-prior over 210 held-out anchors (20%); opens from measured predecessor ibm-granite/granite-3.1-2b-instruct (80%); shrunk 2.9 up toward the measured corpus
Index support
31.8% · limited
Identity binding
Exact catalogue product · ibm-granite/ibm-granite/granite-3.3-2b-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata ibm-granite/granite-3.3-2b-instruct@707f574c62054322f6b5b04b6d075f0a8f05e0f0 (not the evaluation revision)
Index observations used
0
Qualified Index evidence point
13.3
How this position was produced · fused launch placement

No general-family board lists this model yet. Its point estimate is the precision-weighted mean of every channel that spoke for it; each channel’s share is the weight it carried. Independent measurements replace this placement as boards list the model.

Fused estimate
13.3 ± 10.7
Independent share
0%
Shrink toward corpus
+2.9
Optimism haircut
None applied
Method
precision-weighted-v1
Channels fused into this model’s launch placement
ChannelEstimateShare
Publisher corpus prior · not independent
publisher-corpus-prior over 210 held-out anchors
24.5 ± 23.820%
Family succession · not independent
opens from measured predecessor ibm-granite/granite-3.1-2b-instruct
10.4 ± 12.080%
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
—
Evidence status
No admitted measured evidence
General preference
—
Coding
—
Agents & tools
—
Reasoning
—
Evidence breadth
0%
Evidence coverage
0%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
—
Liquidity (providers × uptime)
—
Open reach (HF downloads)
87.4
Surface (context / tools / modalities)
0.0
Freshness
11.1
  • · HF 30d downloads 78641
  • · Catalogue surface
  • · First seen 2025-04-09

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Experimental capability estimate

Estimate policy
11.8
0.0–27.2 uncertainty interval
Excluded from rank
Confidence
75%
Training support
219 models · 128 lineages
Out-of-domain check
in domain
Feature coverage
71%
Lineage-held-out error
8.3 MAE

Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.

Deployment readiness

Metadata index
52.4
partial · 56% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
8.0
Evaluation provenance
0.0

Not yet published: a current serving provider, measured provider uptime, published provider pricing, declared context and output limits, admitted benchmark results, results across several capability areas, results from more than one source, a confident match to its benchmark entries, pinned evaluation dataset versions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
13.7
OpenRouter weekly popularity
Not listed

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

No matched Arena rating

This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.

Market Gravity breakdown

Usage55%
0.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
0.0

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
87.4

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
11.1

Time since first public availability, on a six-month half-life.

Specification

Model ID
ibm-granite/granite-3.3-2b-instruct
Declared output cap
Unknown

OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata

Inputs
Text
Outputs
Text
Cached input tokens
Not offered
First seen on OpenRouter
9 Apr 2025

Capabilities

  • Not supported: Reasoning
  • Not supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
apache-2.0
Pinned revision
707f574c6205
Parameters
2.5B
Architecture
GraniteForCausalLM
Model type
granite
Hugging Face downloads (30d)
79K
Downloads (all time)
2.0M
Likes
87
Repository updated
8 May 2025, 15:01 UTC

Alternatives to granite 3.3 2b instruct, by the numbers

Ranked neighbours

Models within 3 places of #307 on the ModelCap Index.

Other ranked IBM Granite models

The same publisher's other current models with a public Index position.

granite 3.3 2b instruct: common questions

How does granite 3.3 2b instruct rank among AI models?

granite 3.3 2b instruct holds ModelCap Index position #307 of 352 ranked language models as of 6 November 2026, with an Index score of 13.3 (interval 0.0–27.0); evidence: modeled · succession. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does granite 3.3 2b instruct cost per 1M tokens?

No live API price is listed for granite 3.3 2b instruct in the current snapshot as of 6 November 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.

Is granite 3.3 2b instruct open-weight?

Open weights (apache-2.0). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is ibm-granite/granite-3.3-2b-instruct on Hugging Face.

Which benchmarks has granite 3.3 2b instruct been evaluated on?

granite 3.3 2b instruct's Index position rests on the evidence listed on this page; it has no result on the public boards ModelCap tracks as separate leaderboards as of 6 November 2026. The evidence panel names each source and its publication date.

When was granite 3.3 2b instruct released?

granite 3.3 2b instruct first appeared in the catalogue on 9 Apr 2025. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.