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
Quality
MTEB (Multilingual, v2)
Mean(task) · 0–100 · higher is better · this model outlined
- Color = publisher
Source: MTEB results dataset (independent runs, CC0) · publisher-reported where the model card is the only source · other benchmarks and versions are not mixed in
| MTEB (Multilingual, v2) | mean(task) · 768d | 55.96 | independent run |
|---|
Reported by the publisher
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 Granite Embedding 311M Multilingual R2 for retrieval and semantic search: it turns text into 768-dimension vectors.
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.
pip install sentence_transformersfrom 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 serve ibm-granite/granite-embedding-311m-multilingual-r2 --task embed# 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"Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- ibm-granite/granite-embedding-311m-multilingual-r2
- 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.
- Publisher model card
- Hugging Face model page / card · 2026-10-07
- Hugging Face API (parameters, licence, library) · 2026-10-07
- MTEB results dataset (CC0), scores computed by scripts/ingest-mteb-results.mjs · 2026-10-25
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.






























































