Create a model from GGUF

POST

http://localhost:11434/api/create

Create a model from a GGUF file. The files parameter should be filled out with the file name and SHA256 digest of the GGUF file you wish to use. Use /api/blobs/:digest to push the GGUF file to the server before calling this API.

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'http://localhost:11434/api/create' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "llama-2-7b-chat",
    "files": {
        "test.gguf": "sha256:9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd15d6c15b0f00a08"
    }
}'

Response Example

{"status":"parsing GGUF"}
{"status":"using existing layer sha256:432f310a77f4650a88d0fd59ecdd7cebed8d684bafea53cbff0473542964f0c3"}
{"status":"writing manifest"}
{"status":"success"}

Request

Body Params application/json

model

string

required

Example:

llama-2-7b-chat

files

object

required

test.gguf

string

required

SHA256 checksum for model files

Example:

sha256:9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd15d6c15b0f00a08

Match pattern:

^sha256:[a-f0-9]{64}$

Examples

Responses

🟢200Success

application/json

A stream of JSON objects is returned:

Body

status

string

required

Modified at 2025-03-28 02:46:40

Quantize a model

Create a model from a Safetensors directory