Skip to content
Local AI Wizard
Your machine
Theme

Granite Embedding 311M Multilingual R2

IBM · ibm-granite/granite-embedding-311m-multilingual-r2

Weights license: Apache 2.0 · code and components may use other terms

MTEB (Multilingual, v2)56.0 / 100mean(task) · independent run
Memory needed~3 GB8-bit planning estimate · not measured
Parameters0.31 BSee technical details for the basis
Dimensions · context76832,768 tokens · Matryoshka 512/384/256/128

Quality

Reported by the publisher

3 results · IBM's model card · read 2026-10-25
MTEB (eng, v2)
52.6
MTEB (Code, v1)
63.9
ML MTEB Retrieval
63.9

Values as printed on the card, with the publisher's own settings (card section: Evaluation Results › Matryoshka Embeddings Performance); column “granite-embedding-311m-multilingual-r2”. Not comparable across publishers and not used in any ranking. Model card

Quality × memory

No comparable quality × memory pair

Embedding memory estimates cluster at a few GB, so a quality × memory chart would not separate these models; MTEB is ranked above instead.

Consider it for

Consider Granite Embedding 311M Multilingual R2 for retrieval and semantic search: it turns text into 768-dimension vectors.

Check first

The publisher states no memory figure; the hardware list uses a ~3 GB planning estimate, a ceiling and not a measurement. PT-BR is confirmed by a source.

Runs on

Fast memory holds it 119

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 119

Hardware profiles grouped by the embedding planning estimate (8-bit weights, 20% allowance, 2 GB reserve). Not a measured fit.

Measured speed

No published measurement for this checkpoint

Throughput (texts per second) is shown only when a source publishes it with hardware, build and setup. It is never estimated.

How to run

The planning estimate uses 8-bit weights, 20% working allowance and a 2 GB reserve; it is a ceiling, not a measurement.

Runs in
Sentence Transformers, Transformerssource
Languages · PT-BR
200+ languages in pretraining, enhanced support for 52 languages and code, Portuguese included (model card)PT-BR confirmed by a source

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Setup stated first by the source · Sentence Transformers
pip install sentence_transformers
Sentence Transformers · model card · Usage
from sentence_transformers import SentenceTransformer, util

model_path = "ibm-granite/granite-embedding-311m-multilingual-r2"
# Load the Sentence Transformer model
model = SentenceTransformer(model_path)

input_queries = [
    'What is the tallest mountain in Japan?',          # English query
    'Wer hat das Lied Achy Breaky Heart geschrieben?', # German query
    'ドイツの首都はどこですか?',                            # Japanese query
    ]

input_passages = [
    "富士山は、静岡県と山梨県にまたがる活火山で、標高3776.12 mで日本最高峰の独立峰である。",  # Japanese passage
    "Achy Breaky Heart is a country song written by Don Von Tress. Originally titled Don't Tell My Heart and performed by The Marcy Brothers in 1991.",  # English passage
    "Berlin ist die Hauptstadt und ein Land der Bundesrepublik Deutschland. Die Stadt ist mit rund 3,7 Millionen Einwohnern die bevölkerungsreichste Kommune Deutschlands.",  # German passage
    ]

# Cross-lingual retrieval: each query should score highest with its matching passage in a different language
query_embeddings = model.encode(input_queries)
passage_embeddings = model.encode(input_passages)

# calculate cosine similarity — expect high scores on the diagonal (EN→JA, DE→EN, JA→DE)
print(util.cos_sim(query_embeddings, passage_embeddings))
# output: tensor([[0.9393, 0.6899, 0.7627],
#                 [0.6780, 0.9598, 0.7062],
#                 [0.7818, 0.7342, 0.9172]])
vLLM · model card · Optimized Inference and Deployment
vllm serve ibm-granite/granite-embedding-311m-multilingual-r2 --task embed
llama.cpp · model card · Optimized Inference and Deployment
# Convert to GGUF
python convert_hf_to_gguf.py ibm-granite/granite-embedding-311m-multilingual-r2 \
    --outfile granite-embedding-311m-multilingual-r2.gguf

# Generate embeddings
llama-embedding -m granite-embedding-311m-multilingual-r2.gguf -p "example text"

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
embeddings for search (feature extraction)
Library in source
Sentence Transformers, Transformers
Weight license
Apache 2.0
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Parameter basis
Hub safetensors total (311,664,384 parameters, read 2026-10-07 from the Hub API); publishers round it in their names.
Announced
2026-04-29

The card states a 32,768-token sequence length; the MTEB metadata says 8,192. The card value is used. Not found in Ollama's library on 2026-10-07 (its granite-embedding page serves the first generation).

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-07. Each value cites its source (the publisher's card or the MTEB results dataset); estimates are labelled as estimates, and a value no source states stays empty. A repository commit is not a model release date.