Enum QuantFormat 

pub enum QuantFormat {
    FP32,
    FP16,
    BF16,
    Int8,
    Int4,
}

Supported quantization formats

Variants

FP32

Full precision FP32

FP16

Half precision FP16

BF16

Brain float 16

Int8

8-bit integer (GPTQ, etc.)

Int4

4-bit integer

Implementations

impl QuantFormat

pub fn bytes_per_param(&self) -> f32

Bytes per parameter.

pub fn estimate_size_gb(&self, num_params: usize) -> f32

Estimate model size in GB.

Trait Implementations

impl Clone for QuantFormat

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for QuantFormat

impl Debug for QuantFormat

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

Formats the value using the given formatter.

impl Eq for QuantFormat

impl PartialEq for QuantFormat

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for QuantFormat