BAAI

BGE Large EN v1.5

Current

6.1MDownloads633LikesSep 2023Released1K tokensContextMITLicense4 EntryQuality

Get started

— copy & paste to run locally

Ollama

ollama run bge-large-en-v1.5

HuggingFace

huggingface-cli download bge-large-en-v1.5

Quick specs

Parameters0.34B

Architecturedense

Context1K tokens

Modalityembedding

Min RAM0.1 GB

Rec. RAM0.7 GB (F16)

LicenseMIT

FamilyBGE

✓ RAG

About this model

Model List | FAQ | Usage | Evaluation | Train | Contact | Citation | License

•1/9/2024: Release Activation-Beacon, an effective, efficient, compatible, and low-cost (training) method to extend the context length of LLM....
•12/24/2023: Release LLaRA, a LLaMA-7B based dense retriever, leading to state-of-the-art performances on MS MARCO and BEIR. Model and code...
•11/23/2023: Release LM-Cocktail, a method to maintain general capabilities during fine-tuning by merging multiple language models. Technical...
•10/12/2023: Release LLM-Embedder, a unified embedding model to support diverse retrieval augmentation needs for LLMs. Technical Report
•09/15/2023: The technical report and massive training data of BGE has been released

Related models

Quick picks

Intel Arc B580 12GB~$249 — 219 tok/s

RTX 2060 6GB~$349 — 192 tok/s

Best hardware

Top picks for BGE Large EN v1.5

RTX 3050 Ti Laptop 4GBB

Intel Arc A370M 4GBC

Intel Arc A380 6GBC

Intel Arc Pro A40 6GBC

Quantization options

VRAM estimates by quant level

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	0.1 GB	Low	—
Q3_K_S	3	0.2 GB	Low	—
NVFP4	4	0.2 GB	Medium	—
Q4_K_M	4	0.2 GB	Medium	—
Q5_K_M	5	0.2 GB	High	—
Q6_K	6	0.3 GB	High	—
Q8_0	8	0.4 GB	Very High	—
F16	16	0.7 GB	Maximum	—

Hardware compatibility

Fit estimates across all hardware

Open calculator

Computing compatibility...

Memory breakdown

Reference: NVIDIA A10 24GB

Weights0.2 GB

KV Cache0.8 GB

Runtime1.2 GB

Headroom2.4 GB