# Interface: QuantizationConfig

## Hierarchy

- **`QuantizationConfig`**

  ↳ [`MlxQuantizationConfig`](MlxQuantizationConfig)

## Properties

### bits

• `Optional` **bits**: `number`

#### Defined in[[bits.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:930](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L930)

___

### config\_groups

• `Optional` **config\_groups**: `Record`\<`string`, \{ `format?`: `string` ; `targets?`: `string`[] ; `weights?`: \{ `num_bits?`: `number`  }  }\>

#### Defined in[[configgroups.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:935](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L935)

___

### expert\_dtype

• `Optional` **expert\_dtype**: `string`

Routed expert precision when it differs from the main quantizer (e.g. FP4 experts with FP8 attention).

#### Defined in[[expertdtype.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:920](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L920)

___

### format

• `Optional` **format**: `string`

#### Defined in[[format.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:934](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L934)

___

### group\_size

• `Optional` **group\_size**: `number`

#### Defined in[[groupsize.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:928](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L928)

___

### ignore

• `Optional` **ignore**: `string`[]

compressed-tensors names its exclusion list `ignore` rather than `modules_to_not_convert`,
using the same `re:`-prefixed target syntax as `config_groups[].targets`.

#### Defined in[[ignore.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:940](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L940)

___

### load\_in\_4bit

• `Optional` **load\_in\_4bit**: `boolean`

#### Defined in[[loadin4bit.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:931](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L931)

___

### load\_in\_8bit

• `Optional` **load\_in\_8bit**: `boolean`

#### Defined in[[loadin8bit.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:932](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L932)

___

### mode

• `Optional` **mode**: `string`

MLX quantization mode (e.g. `affine`); MLX configs do not declare `quant_method`.

#### Defined in[[mode.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:927](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L927)

___

### modules\_to\_not\_convert

• `Optional` **modules\_to\_not\_convert**: `string`[]

#### Defined in[[modulestonotconvert.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:929](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L929)

___

### quant\_algo

• `Optional` **quant\_algo**: `string`

NVIDIA ModelOpt (`quant_method: "modelopt"`) algorithm, e.g. `"NVFP4"`, `"W4A16_NVFP4"`, `"FP8"`,
or `"MIXED_PRECISION"` — in which case the per-module algorithm is in `quantized_layers`.

#### Defined in[[quantalgo.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:945](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L945)

___

### quant\_method

• `Optional` **quant\_method**: `string`

#### Defined in[[quantmethod.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:918](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L918)

___

### quantized\_layers

• `Optional` **quantized\_layers**: `Record`\<`string`, \{ `quant_algo?`: `string`  }\>

ModelOpt mixed-precision: module name (or a parent module, e.g. `…mlp.experts`) -> its algorithm.

#### Defined in[[quantizedlayers.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:947](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L947)

___

### store\_dtype

• `Optional` **store\_dtype**: `string`

Same role as `expert_dtype` under another name: MiMo-V2.6 is `quant_method: "fp8"` for its
dense layers but stores the routed experts as `store_dtype: "mxfp4"`, packed two per `U8`.

#### Defined in[[storedtype.defined-in]]

[packages/hub/src/lib/parse-safetensors-metadata.ts:925](https://github.com/huggingface/huggingface.js/blob/main/packages/hub/src/lib/parse-safetensors-metadata.ts#L925)