Enum QuantizationScheme 

pub enum QuantizationScheme {
    Int4,
    Int8,
    FP16,
    Dynamic,
    GGUF_Q2_K,
    GGUF_Q3_K,
    GGUF_Q4_K,
    GGUF_Q5_0,
    GGUF_Q6_K,
}

Quantization scheme types

Variants

Int4

Int8

FP16

Dynamic

GGUF_Q2_K

GGUF Q2_K: 2.5625 bits per weight, ultra-low memory

GGUF_Q3_K

GGUF Q3_K: 3.4375 bits per weight, balanced

GGUF_Q4_K

GGUF Q4_K: 4.5 bits per weight, high quality

GGUF_Q5_0

GGUF Q5_0: 5.5 bits per weight, very high quality

GGUF_Q6_K

GGUF Q6_K: 6.5 bits per weight, near-lossless

Trait Implementations

impl Clone for QuantizationScheme

fn clone(&self) -> QuantizationScheme

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizationScheme

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for QuantizationScheme

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for QuantizationScheme

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

Formats the value using the given formatter.

impl PartialEq for QuantizationScheme

fn eq(&self, other: &QuantizationScheme) -> 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 Serialize for QuantizationScheme

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for QuantizationScheme

impl Eq for QuantizationScheme

impl StructuralPartialEq for QuantizationScheme