Sign In
homemodelsimagesvideos3D Modelsarticlescomicsbountieschallengesupdatesshop

QWEN Layerwise for Klein9B (FP8-FP32)

Updated: May 26, 2026

base modelqwenqwen3_8bflux kleinklein9bfp8

Download

1 variant available

fp8 SafeTensor

qwen3_8B_layerwise_FP8.safetensors

8-bit, smaller file • 12.72 GB

Verified:

Type
Checkpoint Trained
Stats

239

Reviews

(8)

Published

May 26, 2026

Base Model

Flux.2 Klein 9B

Training
Steps: 10,000
Epochs: 10
Hash
AutoV2
2CB2427CE6
default creator card background decoration
Reactions - 62291

62.3K

Downloads - 580305

580.3K

Generations - 4872784

4.9M

SDXL Training Contest Participant

License:

FLUX.1 [dev] Non-Commercial License

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

QWEN Layerwise

This is the QWEN 3 8B LLM

Qwen layerwise is the first FP32 training with targeted layers for FLUX Klein that consistently shown improvement vs full BF16 base QWEN on Text

When scoring successes vs failure.

  • If both models failed on text or anatomical errors the result was neutral.

  • If the layerwise model improved text but caused a anatomical error this was a failure

  • Success was only scored if the layerwise model improved text or fixed a glaring error like number of fingers.

The success number exceeded the threshold set for what could just be viewed as random or lucky success vs base BF16.