Enum QuantizationPreference 

#[non_exhaustive]
pub enum QuantizationPreference {
    Auto,
    F32,
    Bf16,
    F16,
    Q4K,
    Q8_0,
}

Caller’s preferred quantization when one is not otherwise specified.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

Auto

Let the source pick a sensible default.

F32

Prefer 32-bit float if available.

Bf16

Prefer 16-bit brain float if available.

F16

Prefer 16-bit IEEE float if available.

Q4K

Prefer GGUF Q4_K if available.

Q8_0

Prefer GGUF Q8_0 if available.

Trait Implementations

impl Clone for QuantizationPreference

fn clone(&self) -> QuantizationPreference

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for QuantizationPreference

impl Debug for QuantizationPreference

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

Formats the value using the given formatter.

impl Default for QuantizationPreference

fn default() -> QuantizationPreference

Returns the “default value” for a type.

impl Eq for QuantizationPreference

impl PartialEq for QuantizationPreference

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for QuantizationPreference