File storage

Concept

Each project have individual storage it didn't share between your projects.

The file storage absolute path is /apps/

workspace : /apps/workspace/

background : /apps/background/

api-service : /apps/api-service/

background will contain you spot job and separate by they task_id.

workspace will contain you run job with latest code only.

api-service will contain you deploy job with latest code only.

---

Bandwidth cost

At the moment, It free.

---

File features

Preview file

Quick preview when file less than 1 mb.

When the file is less than 1 MB, the system will automatically generate a preview for you.

However, if the file is larger than 1 MB, you will need to manually continue with the preview.

Others

• Each file can be downloaded via the GUI.

• "Copy to" is used to copy a file between your projects.

---

Absolute path

The file storage absolute path is /apps/

workspace : /apps/workspace/

background : /apps/background/

api-service : /apps/api-service/

---

Share model weight

We have pre-downloaded AI model weights as shown in the table.

(Permission is read-only)

If you are looking for a new model, please let us know via Discord.

LLM

Model	Absolute path	Option
Qwen3-4B	/share_weights/Qwen3-4B-GGUF/	Qwen3-4B-Q4_K_M.gguf Qwen3-4B-Q8_0.gguf
Qwen3-8B	/share_weights/Qwen3-8B-GGUF/	Qwen3-8B-Q4_K_M.gguf Qwen3-8B-Q8_0.gguf
Qwen3-14B	/share_weights/Qwen3-14B-GGUF/	Qwen3-14B-Q4_K_M.gguf Qwen3-14B-Q8_0.gguf
Qwen3-32B	/share_weights/Qwen3-32B-GGUF/	Qwen3-32B-Q4_K_M.gguf Qwen3-32B-Q8_0.gguf
Qwen3-30B-A3B	/share_weights/Qwen3-30B-A3B-GGUF/	Qwen3-30B-A3B-Q4_K_M.gguf Qwen3-30B-A3B-Q8_0.gguf
Gemma3-12B	/share_weights/Gemma3-12B-GGUF/	gemma-3-12b-it-q4_0.gguf mmproj-model-f16-12B.gguf
Gemma3-27B	/share_weights/Gemma3-27B-GGUF/	gemma-3-27b-it-q4_0.gguf mmproj-model-f16-27B.gguf
typhoon2.1-gemma3-12b	/share_weights/typhoon2.1-gemma3-12b-gguf/	typhoon2.1-gemma3-12b-q4_k_m.gguf

VLM

Model	Absolute path	Option
Qwen2.5-vl-7B	/share_weights/Qwen2.5-VL-7B-Instruct-exl2/	*.safetensors
Qwen2.5-vl-32B	/share_weights/Qwen2.5-VL-32B-Instruct-exl2/	*.safetensors
UI-tars-1.5-7b	/share_weights/UI-TARS-1.5-7B-exl2/	*.safetensors

Embedding

Model	Absolute path	Option
Bge-m3	/share_weights/Bge-m3-GGUF/	bge-m3-Q8_0.gguf
Qwen3-Embedding-0.6B	/share_weights/Qwen3-Embedding-0.6B-GGUF/	Qwen3-Embedding-0.6B-Q8_0.gguf
Qwen3-Embedding-4B	/share_weights/Qwen3-Embedding-4B-GGUF/	Qwen3-Embedding-4B-Q8_0.gguf
Qwen3-Embedding-8B	/share_weights/Qwen3-Embedding-8B-GGUF/	Qwen3-Embedding-8B-Q8_0.gguf