chore(model gallery): add meta-llama_llama-4-scout-17b-16e-instruct (#5141)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-08 10:12:28 +02:00 committed by GitHub
parent 7387932f89
commit 4fbd6609f2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -470,6 +470,31 @@
- filename: Tesslate_Synthia-S1-27b-Q4_K_M.gguf
sha256: d953bf7f802dc68f85a35360deb24b9a8b446af051e82c77f2f0759065d2aa71
uri: huggingface://bartowski/Tesslate_Synthia-S1-27b-GGUF/Tesslate_Synthia-S1-27b-Q4_K_M.gguf
- &llama4
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master"
icon: https://avatars.githubusercontent.com/u/153379578
license: llama4
tags:
- llm
- gguf
- gpu
- cpu
- llama3.3
name: "meta-llama_llama-4-scout-17b-16e-instruct"
urls:
- https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
- https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF
description: |
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
These Llama 4 models mark the beginning of a new era for the Llama ecosystem. We are launching two efficient models in the Llama 4 series, Llama 4 Scout, a 17 billion parameter model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts.
overrides:
parameters:
model: meta-llama_Llama-4-Scout-17B-16E-Instruct-Q3_K_S.gguf
files:
- filename: meta-llama_Llama-4-Scout-17B-16E-Instruct-Q3_K_S.gguf
sha256: 48dfc18d40691b4190b7fecf1f89b78cadc758c3a27a9e2a1cabd686fdb822e3
uri: huggingface://bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q3_K_S.gguf
- &eurollm
name: "eurollm-9b-instruct"
icon: https://openeurollm.eu/_next/static/media/logo-dark.e7001867.svg