chore(model gallery): add aquif-ai_aquif-3.5-8b-think (#6269)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2025-09-15 10:42:42 +02:00
committed by GitHub
parent eadd3d4e46
commit aa7cb7e18c

View File

@@ -2570,6 +2570,21 @@
- filename: minicpm-v-4_5-mmproj-f16.gguf
uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/mmproj-model-f16.gguf
sha256: 7a7225a32e8d453aaa3d22d8c579b5bf833c253f784cdb05c99c9a76fd616df8
- !!merge <<: *qwen3
name: "aquif-ai_aquif-3.5-8b-think"
urls:
- https://huggingface.co/aquif-ai/aquif-3.5-8B-Think
- https://huggingface.co/bartowski/aquif-ai_aquif-3.5-8B-Think-GGUF
description: |
The aquif-3.5 series is the successor to aquif-3, featuring a simplified naming scheme, expanded Mixture of Experts (MoE) options, and across-the-board performance improvements. This release streamlines model selection while delivering enhanced capabilities across reasoning, multilingual support, and general intelligence tasks.
An experimental small-scale Mixture of Experts model designed for multilingual applications with minimal computational overhead. Despite its compact active parameter count, it demonstrates competitive performance against larger dense models.
overrides:
parameters:
model: aquif-ai_aquif-3.5-8B-Think-Q4_K_M.gguf
files:
- filename: aquif-ai_aquif-3.5-8B-Think-Q4_K_M.gguf
sha256: 9e49b9c840de23bb3eb181ba7a102706c120b3e3d006983c3f14ebae307ff02e
uri: huggingface://bartowski/aquif-ai_aquif-3.5-8B-Think-GGUF/aquif-ai_aquif-3.5-8B-Think-Q4_K_M.gguf
- &gemma3
url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
name: "gemma-3-27b-it"