{{if .ModelName}}Edit Model: {{.ModelName}}{{else}}Import New Model{{end}}

Validate{{if .ModelName}}Update{{else}}Create{{end}}

Estimated requirements

Download size: VRAM:

Import from URI

Model URI Search GGUF Models on Hugging Face Browse All Models on Hugging Face

Enter the URI or path to the model file you want to import

Supported URI Formats

HuggingFace

• huggingface://TheBloke/Llama-2-7B-Chat-GGUF

Standard HuggingFace format

• hf://TheBloke/Llama-2-7B-Chat-GGUF

Short HuggingFace format

• https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF

Full HuggingFace URL

HTTP/HTTPS URLs

• https://example.com/model.gguf

Direct download from any HTTPS URL

Local Files

• file:///path/to/model.gguf

Local file path (absolute)

• /path/to/model.yaml

Direct local YAML config file

OCI Registry

• oci://registry.example.com/model:tag

OCI container registry

• ocifile:///path/to/image.tar

Local OCI tarball file

Ollama

• ollama://llama2:7b

Ollama model format

YAML Configuration Files

• https://example.com/model.yaml

Remote YAML config file

• file:///path/to/config.yaml

Local YAML config file

Tip: For HuggingFace models, you can use any of the three formats. The system will automatically detect and download the appropriate model files.

Preferences (Optional)

Common Preferences

Backend Auto-detect (based on URI)llama-cppmlxmlx-vlmtransformersvllmdiffusers

Force a specific backend. Leave empty to auto-detect from URI.

Model Name

Custom name for the model. If empty, the filename will be used.

Description

Custom description for the model. If empty, a default description will be generated.

Quantizations

Preferred quantizations (comma-separated). Examples: q4_k_m, q4_k_s, q3_k_m, q2_k. Leave empty to use default (q4_k_m).

MMProj Quantizations

Preferred MMProj quantizations (comma-separated). Examples: fp16, fp32. Leave empty to use default (fp16).

Embeddings

Enable embeddings support for this model.

Model Type

Model type for transformers backend. Examples: AutoModelForCausalLM, SentenceTransformer, Mamba, MusicgenForConditionalGeneration. Leave empty to use default (AutoModelForCausalLM).

Pipeline Type

Pipeline type for diffusers backend. Examples: StableDiffusionPipeline, StableDiffusion3Pipeline, FluxPipeline. Leave empty to use default (StableDiffusionPipeline).

Scheduler Type

Scheduler type for diffusers backend. Examples: k_dpmpp_2m, euler_a, ddim. Leave empty to use model default.

Enable Parameters

Enabled parameters for diffusers backend (comma-separated). Leave empty to use default (negative_prompt,num_inference_steps).

CUDA

Enable CUDA support for GPU acceleration with diffusers backend.

Custom Preferences Add Custom

Add custom key-value pairs for advanced configuration

YAML Configuration Editor

Format Copy