Enum Quantization 

pub enum Quantization {
    F16,
    Q8_0,
    Q6_K,
    Q5_K_M,
    Q5_K_S,
    Q4_K_M,
    Q4_K_S,
    Q4_0,
    Q3_K_S,
    Q3_K_M,
    Q3_K_L,
    Q2_K,
    IQ2_XS,
    IQ3_XS,
    IQ4_NL,
}

Quantization level for GGUF models.

Variants

F16

Float 16 (full precision, largest)

Q8_0

8-bit quantization

Q6_K

6-bit K-quant medium

Q5_K_M

5-bit K-quant medium (good balance)

Q5_K_S

5-bit K-quant small

Q4_K_M

4-bit K-quant medium (recommended)

Q4_K_S

4-bit K-quant small

Q4_0

4-bit

Q3_K_S

3-bit K-quant small

Q3_K_M

3-bit K-quant medium

Q3_K_L

3-bit K-quant large

Q2_K

2-bit K-quant (smallest, lowest quality)

IQ2_XS

IQ2 - intelligent 2-bit

IQ3_XS

IQ3 - intelligent 3-bit

IQ4_NL

IQ4 - intelligent 4-bit

Implementations

impl Quantization

pub fn memory_multiplier(&self) -> f32

Memory multiplier relative to model size. Lower = less memory needed.

pub fn quality_rating(&self) -> u8

Quality rating (1-5, higher = better).

Trait Implementations

impl Clone for Quantization

fn clone(&self) -> Quantization

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Quantization

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

Formats the value using the given formatter.

impl Display for Quantization

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

Formats the value using the given formatter.

impl Hash for Quantization

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

where __H: Hasher,

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 Quantization

fn eq(&self, other: &Quantization) -> 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 Copy for Quantization

impl Eq for Quantization

impl StructuralPartialEq for Quantization