Struct QuantModelDesc 

pub struct QuantModelDesc {
    pub architecture: String,
    pub n_embd: u32,
    pub n_ff: u32,
    pub n_layer: u32,
    pub n_head: u32,
    pub n_head_kv: u32,
    pub n_expert: u32,
    pub n_embd_head_k: u32,
    pub n_embd_head_v: u32,
}

Shape of a synthetic model, for previewing a quantization plan without a real checkpoint on disk.

Upstream marks llama_quant_model_from_metadata as being for testing; it is exposed here for the same reason — it lets you ask “what would a Q4_K_M of a model this shape look like?” without downloading one.

Fields

architecture: String

Architecture name, e.g. "llama".

n_embd: u32

Embedding dimension.

n_ff: u32

Feed-forward dimension.

n_layer: u32

Number of layers.

n_head: u32

Number of attention heads.

n_head_kv: u32

Number of key/value heads.

n_expert: u32

Number of experts (0 for a dense model).

n_embd_head_k: u32

Per-head key dimension.

n_embd_head_v: u32

Per-head value dimension.

Implementations

impl QuantModelDesc

pub fn llama(n_embd: u32, n_ff: u32, n_layer: u32, n_head: u32) -> Self

A dense llama-shaped descriptor with the given dimensions.

pub fn build(&self) -> Result<LlamaModel, QuantPreviewError>

Build a synthetic model from this descriptor.

The returned model owns llama.cpp memory and frees it on drop, exactly like a loaded one — it simply has no weights.

Errors

Returns QuantPreviewError::MockModel if llama.cpp rejects the descriptor, or QuantPreviewError::Nul for a bad architecture name.

Trait Implementations

impl Clone for QuantModelDesc

fn clone(&self) -> QuantModelDesc

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantModelDesc

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

Formats the value using the given formatter.

impl Eq for QuantModelDesc

impl PartialEq for QuantModelDesc

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for QuantModelDesc