FLUX.2 Klein 4B GGUF bundle for NovelAide

This public repository contains the exact immutable three-file bundle used by NovelAide Desktop with stable-diffusion.cpp. NovelAide mirrors these files byte-for-byte and has not retrained or requantized them.

File Upstream repository Upstream revision Bytes SHA-256
flux-2-klein-4b-Q4_0.gguf leejet/FLUX.2-klein-4B-GGUF 3b1f5a9dc3abb32238b053aeb3d823c30afdacbd 2,460,378,560 d1023499ef3f2f82ff7c50e6778495195c1b6cc34835741778868428111f9ff4
Qwen3-4B-Q4_K_M.gguf unsloth/Qwen3-4B-GGUF 22c9fc8a8c7700b76a1789366280a6a5a1ad1120 2,497,281,312 f6f851777709861056efcdad3af01da38b31223a3ba26e61a4f8bf3a2195813a
full_encoder_small_decoder.safetensors black-forest-labs/FLUX.2-small-decoder a3efc24f613ef42d9428af62fdbd6f5fd8856c4a 249,519,092 ea4273f02d1fafbf8e1d1c2cf6018ed8748652eb0bf34f2dd91171f16f15ab62

The base FLUX.2 Klein 4B model is distributed under Apache-2.0. Refer to the upstream repositories for their model cards, licenses, and acceptable-use guidance.

Downloads last month
275
GGUF
Model size
4B params
Architecture
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for novelaide/FLUX.2-klein-4B-GGUF

Quantized
(32)
this model