Model reference · open weights

FLUX.2-klein-SDNQ-dynamic

FLUX.2-klein-SDNQ-dynamic is an open-weight image model from Disty0, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Licence fee required Image Disty0 1 variants 28k downloads/mo
Request a licence + hosting quote All served models Not on the shared API today — deployed on request.

About

What FLUX.2-klein-SDNQ-dynamic is

Dynamic 4 bit quantization of black-forest-labs/FLUX.2-klein-4B using SDNQ. This model uses per layer fine grained quantization. What dtype to use for a layer is selected dynamically by trial and error until the std normalized mse loss is lower than the selected threshold. Minimum allowed dtype is set to uint4 and std normalized mse loss threshold is set to 1e-2. This created a mixed precision model with uint4 and int5 dtypes. SVD quantization is disabled. Usage: Original BF16 vs SDNQ quantization comparison:

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerDisty0
TypeImage models
Parameters (lead)2.2B
Variants1
Runs withdiffusers
Based onblack-forest-labs/FLUX.2-klein-4B
Released2026-01-15
Popularity28k downloads / month
Likes19
LicenceCommercial licence needed

How it works

How image models work

Text promptwhat to makeText encoderunderstands itDiffusion stepsdenoise to pixelsImagePNG / JPEGA diffusion model starts from noise and denoises it, guided by your prompt, into a finished image.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
FLUX.2-klein-4B-SDNQ-4bit-dynamic2.2BBF16~5 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys flux-2-klein-sdnq-dynamic for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (flux-2-klein-sdnq-dynamic below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/images/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"flux-2-klein-sdnq-dynamic","prompt":"a red bicycle","size":"1024x1024"}'

Details

Languages, data & research

Tags

diffusers safetensors sdnq flux 4-bit diffusers:Flux2KleinPipeline 8-bit

Licence

Commercial licence needed

The weights are open but apache-2.0 needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗

Sources

Weights & code

Want FLUX.2-klein-SDNQ-dynamic on EU-owned hardware?

Request a licence + hosting quote See what’s served now

Explore

More image models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms