Specification

Release date: 4 Dec 2024
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Openness: open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
License: apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Architecture: RobertaModel
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Parameters: 124.7M
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Languages: en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Quantization format: onnx
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
File size: 0.3 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Hugging Face repo: ibm-granite/granite-embedding-125m-english
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Pipeline tag: sentence-similarity
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Model card: huggingface.co/ibm-granite/granite-embedding-125m-english
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Downloads: 119,044
Source:Hugging Face Hub (public pages, model cards, papers)T2observed just nowmedium
Likes: 38
Source:Hugging Face Hub (public pages, model cards, papers)T2observed just nowmedium
Gated: No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Hf inference providers: hf-inference
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Is quantized: Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Last modified: 2025-08-19T01:31:48+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Library name: sentence-transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Downloads all time: 885,879
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Model type: roberta
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Tags: sentence-transformers, pytorch, onnx, safetensors, roberta, feature-extraction, language, granite, embeddings, mteb, transformers, sentence-similarity, en, model-index, text-embeddings-inference
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Weights dtype: BF16
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

22

Source tiers

T222

Freshest observation

just now

Conflicts

None

Modalities

Modalities unavailable.

Capabilities

Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable

No capability flags have been observed from a source yet — we do not infer them.

Languages: en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.

Current prices

No current prices recorded

Prices appear when a provider publishes a public pricing page we crawl.

Price history

Estimated

Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.

Estimated hardware fit
Hardware	Quantization	Memory	Est. need	Fits
NVIDIA DGX B200	4bit	1,440 GB	0.6 GB	Yes
Apple M3 Ultra	4bit	—	0.6 GB	Yes
Mac Studio (Apple M5 Ultra)	4bit	—	0.6 GB	Yes
AMD Instinct MI325X	4bit	256 GB	0.6 GB	Yes
AMD Instinct MI300X	4bit	192 GB	0.6 GB	Yes
Apple M2 Ultra	4bit	—	0.6 GB	Yes
NVIDIA B200	4bit	180 GB	0.6 GB	Yes
NVIDIA H200	4bit	141 GB	0.6 GB	Yes
NVIDIA H200 NVL	4bit	141 GB	0.6 GB	Yes
Apple M1 Ultra	4bit	—	0.6 GB	Yes
Apple M3 Max	4bit	—	0.6 GB	Yes
Apple M4 Max	4bit	—	0.6 GB	Yes
Mac Studio (Apple M5 Max)	4bit	—	0.6 GB	Yes
MacBook Pro (Apple M5 Max)	4bit	—	0.6 GB	Yes
NVIDIA DGX Spark	4bit	128 GB	0.6 GB	Yes
Apple M2 Max	4bit	—	0.6 GB	Yes
NVIDIA H100 NVL	4bit	94 GB	0.6 GB	Yes
NVIDIA A100 80GB	4bit	80 GB	0.6 GB	Yes
NVIDIA H100 SXM	4bit	80 GB	0.6 GB	Yes
Apple M1 Max	4bit	—	0.6 GB	Yes
Apple M4 Pro	4bit	—	0.6 GB	Yes
Mac mini (Apple M5 Pro)	4bit	—	0.6 GB	Yes
MacBook Pro (Apple M5 Pro)	4bit	—	0.6 GB	Yes
Apple M3 Pro	4bit	—	0.6 GB	Yes
Apple M1 Pro	4bit	—	0.6 GB	Yes
Apple M2 Pro	4bit	—	0.6 GB	Yes
Apple M4	4bit	—	0.6 GB	Yes
iMac (Apple M4)	4bit	—	0.6 GB	Yes
Mac mini (Apple M6)	4bit	—	0.6 GB	Yes
MacBook Air (Apple M5)	4bit	—	0.6 GB	Yes
MacBook Pro (Apple M5)	4bit	—	0.6 GB	Yes
NVIDIA GeForce RTX 5090	4bit	32 GB	0.6 GB	Yes
Apple M2	4bit	—	0.6 GB	Yes
Apple M3	4bit	—	0.6 GB	Yes
NVIDIA GeForce RTX 3090	4bit	24 GB	0.6 GB	Yes
NVIDIA GeForce RTX 4090	4bit	24 GB	0.6 GB	Yes
Apple M1	4bit	—	0.6 GB	Yes

No lineage recorded

Lineage comes from explicit `derived_from`, `fine_tuned_from`, `distilled_from` and `quantized_from` relations stated by sources.

Papers 2

arXiv:2502.20204Active
35
arXiv:0000.00000Active
35

Repositories 0

No repositories linked yet.

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Is quantized

1 claims · 1 propertiesShow all properties

Is quantizedis_quantized1

Claim history for Is quantized
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:36 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

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 →

11 Sept 2026
New modelModelgranite-embedding-125m-englishIBM
New model: granite-embedding-125m-english (IBM)
huggingface
huggingface.co

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=ibm-granite&p=0&sort=downloads	listing	T2· Quality secondary	just now	3
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/ibm-granite/granite-embedding-125m-english	model_page	T2· Quality secondary	1 h ago	2

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