Skip to content

SDNQ Quantization

SD.Next Quantization provides full cross-platform quantization to reduce memory usage and increase performance for any device.
SDNQ was originally based on NNCF, but has been re-implemented, optimized and evolved enough to become its own quantization method!

Usage

  1. Go into Quantization Settings
  2. Enable the desired Quantization options under the SDNQ menu
    (Model, Transformer, TE and LLM are the main targets for most use cases)
  3. Reload the model

Features

  • SDNQ is fully cross-platform, supports all GPUs and includes many quantization methods:
  • 8-bit, 6-bit, 4-bit, 2-bit and 1-bit int and uint
  • 8-bit e5, e4 and fnuz float
    note: int8 is very close to the original 16 bit quality
  • Supports nearly all model types
  • Supports compute optimizations using Triton via torch.compile
  • Supports Quantized MatMul with significant speedups on INT8 or FP8 supported GPUs
  • Supports on the fly quantization during model load with DiT models (called as pre mode)
  • Supports quantization for the convolutional layers with UNet models
  • Supports post load quantization for any model
  • Supports on the fly usage of LoRa models
  • Supports balanced offload

Options

Quantization enabled

Used to decide which parts of the model will get quantized.
Recommended options are Model and TE with post mode or Transformer, TE and LLM on pre mode.
Default is none.

Model is used quantize the UNet on post mode or every model part on pre mode.
Transformer is used to quantize the DiT models.
VAE is used to quantize the VAE. Using the VAE option is not recommended.
TE is used to quantize the Text Encoders.
Video is used to quantize the Video models.
LLM is used to quantize the LLM part of the models that uses LLMs as Text Encoders.
ControlNet is used to quantize ControlNets.

Note: VAE Upcast has to be set to false if you use the VAE option with FP16.
If you get black images with SDXL models, use the FP16 Fixed VAE.

Quantization mode

Used to decide when the quantization step will happen on model load.
Pre mode will quantize the model while the model is loading. Reduces system RAM usage.
Post mode will quantize the model after the model is loaded into system RAM.
Pre mode is compatible with DiT and Video models like Flux but older UNet models like SDXL are only compatible with post mode.
Default is pre.

Quantization type

Used to decide the data type used to store the model weights.
Recommended types are int8 for 8 bit, int6 for 6 bit, float8_e4m3fn for fp8 and uint4 for 4 bit.
Default is int8.

INT8 quants have very similar quality to the full 16 bit precision while using 2 times less memory.
INT6 quants are the middle ground. Similar quality to to the full 16 bit precision while using 2.7 times less memory.
INT4 quants have lower quality and less performance but uses 3.6 times less memory.
FP8 quants have similar quality to INT6 but with the same memory usage as INT8.

Unsigned quants have the extra u added to the start of their name while the symetric quants don't have any prefix.
Unsigned (asymetric) types: uint8, uint6, uint4, uint2 and uint1
Symetric types: int8, int6, int4, float8_e4m3fn, float8_e5m2, float8_e4m3fnuz and float8_e5m2fnuz

Unsigned quants uses unsigned integers, meaning they can't store negative values and will use another variable called zero point for this purpose.
Symetric quants can store negative and positive values meaning they don't have extra zero point value and they run faster than unsigned quants because of this.

int8 uses int8 and has -128 to 127 range.
uint8 uses uint8 and has 0 to 255 range.
int6 uses four int6 values packed into three uint8 values and has -32 to 31 range.
uint6 uses four uint6 values packed into three uint8 values and has 0 to 63 range.
int4 uses two int4 values packed into a single uint8 value and has -8 to 7 range.
uint4 uses two uint4 values packed into a single uint8 value and has 0 to 15 range.
int2 uses four int2 values packed into a single uint8 value and has -2 to 1 range.
uint2 uses four uint2 values packed into a single uint8 value and has 0 to 3 range.
uint1 uses boolean and has 0 to 1 range.
float8_e4m3fn uses float8_e4m3fn and has -448 to 448 range.
float8_e5m2 uses float8_e5m2 and has -57344 to 57344 range.
float8_e4m3fnuz uses float8_e4m3fnuz and has -240 to 240 range.
float8_e5m2fnuz uses float8_e5m2fnuz and has -57344 to 57344 range.

Group size

Used to decide how many elements of a tensor will share the same quantization group.
Higher values have better performance but less quality.
Default is 0, meaning it will decide the group size based on your quantization type setting.
INT8, INT6 and FP8 quants won't use any grouping by default.
Other quant types will use this formula to find the group size: 2 ** (2 + number_of_bits)
Setting the group size to -1 will disable grouping.

Quantize the convolutional layers

Enabling this option will quantize the convolutional layers in UNet models too.
Has much better memory savings but lower quality.
Convolutions won't use group sizes with INT8 and FP8 quants.
Convolutions will use this formula to find the group size with other quant types: 2 ** (1 + number_of_bits)
Convolutions will use uint4 with uint2, int2 and uint1 quants.
Disabled by default.

Decompress using torch.compile

Uses Triton via torch.compile on the decompression step.
Has significantly higher performance.
This setting requires a full restart of the webui to apply.
Enabled by default if Triton is available.

Use Quantized MatMul

Enabling this option will use quantized INT8 or FP8 MatMul instead of BF16 / FP16.
Has significantly higher performance on GPUs with INT8 or FP8 support.
Recommended quant type to use with this option is int8 because INT8 matmul tends to be faster than FP8.
Quantized INT8 MatMul is only compatible with int8, int4 and int2 quant types.
Quantized FP8 MatMul is only compatible with float8_e4m3fn and float8_e5m2 quant types.
Groups sizes will be disabled when Quantized MatMul is enabled.
Disabled by default.

Use Quantized MatMul with convolutional layers

Same as Use Quantized MatMul but for the convolutional layers with UNets like SDXL.
Disabled by default.

Quantize with the GPU

Enabling this option will use the GPU with the quantization calculations on model load.
Can be faster with weak CPUs but can also be slower because of GPU to CPU communication overhead.
Enabled by default.

When Model load device map in the Models & Loading settings is set to default or cpu this option will send a part of the model weights to the GPU and quantize it, then will send it back to the CPU right away.
If device map is set to gpu, model weights will be loaded directly into GPU and the quantized model weights will be kept in the GPU until the quantization of the current model part is over.

If Model offload mode is set to none, quantized model weights will be sent to the GPU regardless of this setting and will stay in the GPU.
If Model offload mode is set to model, quantized model weights will be sent to the GPU regardless of this setting and will be sent back to the CPU after the quantization of the current model part is over.

Decompress using full precision

Enabling this option will use FP32 on the decompression step.
Has higher quality outputs but lower performance.
Disabled by default.