量化模型

POST

http://localhost:11434/api/create

Quantize a non-quantized model.

请求示例

Shell

JavaScript

Java

Swift

curl --location --request POST 'http://localhost:11434/api/create' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "llama3.1:quantized",
    "from": "llama3.1:8b-instruct-fp16",
    "quantize": "q4_K_M"
}'

响应示例

{"status":"quantizing F16 model to Q4_K_M"}
{"status":"creating new layer sha256:667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29"}
{"status":"using existing layer sha256:11ce4ee3e170f6adebac9a991c22e22ab3f8530e154ee669954c4bc73061c258"}
{"status":"using existing layer sha256:0ba8f0e314b4264dfd19df045cde9d4c394a52474bf92ed6a3de22a4ca31a177"}
{"status":"using existing layer sha256:56bb8bd477a519ffa694fc449c2413c6f0e1d3b1c88fa7e3c9d88d3ae49d4dcb"}
{"status":"creating new layer sha256:455f34728c9b5dd3376378bfb809ee166c145b0b4c1f1a6feca069055066ef9a"}
{"status":"writing manifest"}
{"status":"success"}

请求参数

Body 参数application/json

model

enum<string>

必需

枚举值:

llama3.1:quantized

示例值:

llama3.1:quantized

from

enum<string>

必需

枚举值:

llama3.1:8b-instruct-fp16

示例值:

llama3.1:8b-instruct-fp16

quantize

enum<string>

必需

枚举值:

q4_K_M

示例值:

q4_K_M

示例

返回响应

🟢200Success

application/json

A stream of JSON objects is returned:

Body

status

string

必需

修改于 2025-03-27 09:19:37

创建新模型

从 GGUF 文件创建模型