Enum EmbeddingModel 

pub enum EmbeddingModel {
    BGESmallENV15,
    AllMiniLML6V2,
    AllMiniLML6V2Q,
    AllMiniLML12V2,
    AllMiniLML12V2Q,
    AllMpnetBaseV2,
    BGEBaseENV15,
    BGEBaseENV15Q,
    BGELargeENV15,
    BGELargeENV15Q,
    BGESmallENV15Q,
    BGESmallZHV15,
    BGELargeZHV15,
    BGEM3,
    NomicEmbedTextV1,
    NomicEmbedTextV15,
    NomicEmbedTextV15Q,
    ParaphraseMLMiniLML12V2,
    ParaphraseMLMiniLML12V2Q,
    ParaphraseMLMpnetBaseV2,
    ModernBertEmbedLarge,
    MultilingualE5Small,
    MultilingualE5Base,
    MultilingualE5Large,
    MxbaiEmbedLargeV1,
    MxbaiEmbedLargeV1Q,
    GTEBaseENV15,
    GTEBaseENV15Q,
    GTELargeENV15,
    GTELargeENV15Q,
    ClipVitB32,
    JinaEmbeddingsV2BaseCode,
    JinaEmbeddingsV2BaseEN,
    EmbeddingGemma300M,
    SnowflakeArcticEmbedXS,
    SnowflakeArcticEmbedXSQ,
    SnowflakeArcticEmbedS,
    SnowflakeArcticEmbedSQ,
    SnowflakeArcticEmbedM,
    SnowflakeArcticEmbedMQ,
    SnowflakeArcticEmbedMLong,
    SnowflakeArcticEmbedMLongQ,
    SnowflakeArcticEmbedL,
    SnowflakeArcticEmbedLQ,
}

Embedding model catalog with metadata for all supported ONNX models.

Variant names match fastembed::EmbeddingModel exactly for trivial 1:1 mapping.

Variants

BGESmallENV15

BGE Small EN v1.5 — fast 384-dim English model (default).

AllMiniLML6V2

sentence-transformers all-MiniLM-L6-v2 (384-dim).

AllMiniLML6V2Q

Quantized all-MiniLM-L6-v2 (384-dim).

AllMiniLML12V2

sentence-transformers all-MiniLM-L12-v2 (384-dim).

AllMiniLML12V2Q

Quantized all-MiniLM-L12-v2 (384-dim).

AllMpnetBaseV2

sentence-transformers all-mpnet-base-v2 (768-dim).

BGEBaseENV15

BGE Base EN v1.5 (768-dim).

BGEBaseENV15Q

Quantized BGE Base EN v1.5 (768-dim).

BGELargeENV15

BGE Large EN v1.5 (1024-dim).

BGELargeENV15Q

Quantized BGE Large EN v1.5 (1024-dim).

BGESmallENV15Q

Quantized BGE Small EN v1.5 (384-dim).

BGESmallZHV15

BGE Small ZH v1.5 — Chinese model (512-dim).

BGELargeZHV15

BGE Large ZH v1.5 — Chinese model (1024-dim).

BGEM3

BGE M3 — multilingual, 100+ languages, 8192 context (1024-dim).

NomicEmbedTextV1

Nomic Embed Text v1 — 8192 context English model (768-dim).

NomicEmbedTextV15

Nomic Embed Text v1.5 — 8192 context English model (768-dim).

NomicEmbedTextV15Q

Quantized Nomic Embed Text v1.5 (768-dim).

ParaphraseMLMiniLML12V2

Paraphrase multilingual MiniLM-L12-v2 (384-dim).

ParaphraseMLMiniLML12V2Q

Quantized paraphrase multilingual MiniLM-L12-v2 (384-dim).

ParaphraseMLMpnetBaseV2

Paraphrase multilingual mpnet-base-v2 (768-dim).

ModernBertEmbedLarge

ModernBERT Embed Large (1024-dim).

MultilingualE5Small

Multilingual E5 Small (384-dim).

MultilingualE5Base

Multilingual E5 Base (768-dim).

MultilingualE5Large

Multilingual E5 Large (1024-dim).

MxbaiEmbedLargeV1

Mixedbread mxbai-embed-large-v1 (1024-dim).

MxbaiEmbedLargeV1Q

Quantized mxbai-embed-large-v1 (1024-dim).

GTEBaseENV15

Alibaba GTE Base EN v1.5 (768-dim).

GTEBaseENV15Q

Quantized Alibaba GTE Base EN v1.5 (768-dim).

GTELargeENV15

Alibaba GTE Large EN v1.5 (1024-dim).

GTELargeENV15Q

Quantized Alibaba GTE Large EN v1.5 (1024-dim).

ClipVitB32

OpenAI CLIP ViT-B/32 text encoder (512-dim).

JinaEmbeddingsV2BaseCode

Jina Embeddings v2 Base for code (768-dim).

JinaEmbeddingsV2BaseEN

Jina Embeddings v2 Base for English (768-dim).

EmbeddingGemma300M

Google EmbeddingGemma 300M (768-dim).

SnowflakeArcticEmbedXS

Snowflake Arctic Embed XS (384-dim).

SnowflakeArcticEmbedXSQ

Quantized Snowflake Arctic Embed XS (384-dim).

SnowflakeArcticEmbedS

Snowflake Arctic Embed S (384-dim).

SnowflakeArcticEmbedSQ

Quantized Snowflake Arctic Embed S (384-dim).

SnowflakeArcticEmbedM

Snowflake Arctic Embed M (768-dim).

SnowflakeArcticEmbedMQ

Quantized Snowflake Arctic Embed M (768-dim).

SnowflakeArcticEmbedMLong

Snowflake Arctic Embed M Long — 2048 context (768-dim).

SnowflakeArcticEmbedMLongQ

Quantized Snowflake Arctic Embed M Long (768-dim).

SnowflakeArcticEmbedL

Snowflake Arctic Embed L (1024-dim).

SnowflakeArcticEmbedLQ

Quantized Snowflake Arctic Embed L (1024-dim).

Implementations

impl EmbeddingModel

pub const ALL: &[Self]

All supported models.

pub const fn dimension(self) -> usize

Embedding dimensionality.

pub const fn description(self) -> &'static str

Short human-readable description.

pub const fn query_prefix(self) -> Option<&'static str>

Optional prefix prepended to query texts before embedding.

pub const fn doc_prefix(self) -> Option<&'static str>

Optional prefix prepended to document texts before embedding.

pub const fn size_mb(self) -> usize

Approximate ONNX model size in MB.

pub const fn model_id(self) -> &'static str

Original HuggingFace model name (e.g. "BAAI/bge-small-en-v1.5").

This is the canonical model identifier from the original publisher. For the actual HuggingFace repository used by fastembed-rs for downloads and caching, use model_code instead.

pub const fn max_seq_length(self) -> usize

Maximum token context per model.

pub const fn is_quantized(self) -> bool

Whether this is a quantized model (Q suffix).

pub const fn is_image_model(self) -> bool

Whether this model handles image inputs (CLIP).

pub const fn model_code(self) -> &'static str

HuggingFace model code used by fastembed-rs for downloads and caching (e.g. "Xenova/bge-small-en-v1.5").

This is the actual repository identifier that hf-hub uses when downloading model weights. Differs from model_id when the ONNX conversion lives in a separate repo (e.g. Qdrant/…, Xenova/…, onnx-community/…).

pub fn as_str(self) -> &'static str

String representation matching the enum variant name.

pub fn parse(s: &str) -> Result<Self, String>

Parse a model name (case-insensitive).

pub fn as_fastembed(self) -> EmbeddingModel

Map to fastembed::EmbeddingModel.

Only available when an ONNX embedding feature is enabled (embedding-fastembed or embedding-fastembed-dynamic-linking).

Trait Implementations

impl Clone for EmbeddingModel

fn clone(&self) -> EmbeddingModel

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for EmbeddingModel

impl Debug for EmbeddingModel

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for EmbeddingModel

fn default() -> EmbeddingModel

Returns the “default value” for a type.

impl Display for EmbeddingModel

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Eq for EmbeddingModel

impl FromStr for EmbeddingModel

type Err = String

The associated error which can be returned from parsing.

fn from_str(s: &str) -> Result<Self, Self::Err>

Parses a string s to return a value of this type.

impl Hash for EmbeddingModel

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for EmbeddingModel

fn eq(&self, other: &EmbeddingModel) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for EmbeddingModel