You can deploy this model and start earning money today!

daolsoft/
geulbom-qwen3.5-4b-gguf

Name: geulbom-qwen3.5-4b-gguf
Availability: InStock

Views

No views yet

Geulbom Qwen3.5 4B Q4_K_M

This is Daolsoft's reproducible GGUF conversion of the official Qwen/Qwen3.5-4B weights for the local, text-only AI features planned for Geulbom. It is not an official Qwen release and does not include a multimodal projector.

Reproducibility

Item	Value
Source revision	`851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a`
llama.cpp release	`b10276`
llama.cpp revision	`6ea215d171fd31df943bf1ac8227129f2b963160`
Quantization	`Q4_K_M`
File	`qwen3.5-4b-q4_k_m.gguf`
Size	`2,783,446,688` bytes
SHA-256	`1e7a30ab183568d76c114323b8ae082f153a8913e391ed801f429b3bb4222339`

The conversion runs in the pinned Docker environment in the Geulbom repository:

text

docker compose build ai-model-build
docker compose run --rm ai-model-build
docker compose run --rm --entrypoint bash ai-model-build /workspace/build/ai/smoke-test-model.sh

The smoke test loads the generated file with the same pinned llama.cpp release on CPU and verifies a Korean chat completion. Product release still requires Geulbom's full Korean document quality, Windows runtime, memory, cancellation, and repeated-stability test gates.

License

The source model is provided under Apache License 2.0. Review the official source repository's license and model card before redistribution or use.

daolsoft/geulbom-qwen3.5-4b-gguf

Geulbom Qwen3.5 4B Q4_K_M

Reproducibility

License

daolsoft/
geulbom-qwen3.5-4b-gguf