Welcome to your LocalAI instance!

The FOSS alternative to OpenAI, Claude, ...

Documentation

Operations in progress

vulpecula-4b (from the 'localai' repository)

Installation

Installed models

We have 100 pre-loaded models available.

Model Name Backend Actions

ai21labs_ai21-jamba-reasoning-3b

llama-cpp

allura-org_q3-30b-a3b-pentiment

auto

allura-org_remnant-qwen3-8b

auto

amoral-qwen3-14b

auto

arliai-llama-3-8b-formax-v1.0

auto

arliai_llama-3.3-70b-arliai-rpmax-v1.4

auto

badger-lambda-llama-3-8b

auto

baidu_ernie-4.5-21b-a3b-thinking

llama-cpp

black-ink-guild_pernicious_prophecy_70b

auto

calme-2.8-qwen2-7b

auto

claria-14b

auto

copus-2x8b-i1

auto

darkens-8b

auto

dolphin-2.9-llama3-8b:Q6_K

auto

dolphin-2.9.2-phi-3-Medium-abliterated

auto

dolphin-2.9.2-phi-3-medium

auto

dolphin-2.9.2-qwen2-7b

auto

dreamshaper

diffusers

duloxetine-4b-v1-iq-imatrix

auto

falcon3-10b-instruct

auto

falcon3-1b-instruct

auto

falcon3-1b-instruct-abliterated

auto

falcon3-3b-instruct

auto

fast-math-qwen3-14b

auto

furina-8b

auto

goekdeniz-guelmez_josiefied-qwen3-8b-abliterated-v1

auto

gpt-4

auto

gpt-4-vision-preview

llama-cpp

gryphe_pantheon-proto-rp-1.8-30b-a3b

auto

huihui-ai_qwen3-14b-abliterated

auto

ibm-granite_granite-4.0-h-micro

llama-cpp

ibm-granite_granite-4.0-h-small

llama-cpp

ibm-granite_granite-4.0-h-tiny

llama-cpp

ibm-granite_granite-4.0-micro

llama-cpp

jina-reranker-v1-base-en

rerankers

josiefied-qwen3-8b-abliterated-v1

auto

jsl-medllama-3-8b-v2.0

auto

kalomaze_qwen3-16b-a3b

auto

l3-umbral-mind-rp-v1.0-8b-iq-imatrix

auto

l3.3-70b-magnum-v4-se

auto

llama-3-8b-instruct-dpo-v0.3-32k

auto

llama-3-sec-chat

auto

llama-salad-8x8b

auto

magnum-v3-34b

auto

mahou-1.2-llama3-8b

auto

master-yi-9b

auto

meta-llama-3.1-8b-claude-imat

auto

microsoft_phi-4-mini-instruct

auto

microsoft_phi-4-mini-reasoning

auto

microsoft_phi-4-reasoning

auto

microsoft_phi-4-reasoning-plus

auto

mlabonne_qwen3-14b-abliterated

auto

mlabonne_qwen3-4b-abliterated

auto

mlabonne_qwen3-8b-abliterated

auto

nyun-llama3-62b

auto

opengvlab_internvl3_5-30b-a3b

llama-cpp

opengvlab_internvl3_5-30b-a3b-q8_0

llama-cpp

qwen-3-32b-medical-reasoning-i1

auto

qwen3-0.6b

auto

qwen3-1.7b

auto

qwen3-14b

auto

qwen3-14b-griffon-i1

auto

qwen3-14b-uncensored

auto

qwen3-30b-a1.5b-high-speed

auto

qwen3-30b-a3b

auto

qwen3-30b-a3b-abliterated

auto

qwen3-32b

auto

qwen3-4b

auto

qwen3-4b-esper3-i1

auto

qwen3-8b

auto

qwen3-8b-jailbroken

auto

replete-coder-instruct-8b-merged

auto

sd-1.5-ggml

stablediffusion-ggml

sd-3.5-large-ggml

stablediffusion-ggml

sd-3.5-medium-ggml

stablediffusion-ggml

shuttleai_shuttle-3.5

auto

sicariussicariistuff_phi-line_14b

auto

smolvlm-256m-instruct

auto

smolvlm-500m-instruct

auto

smolvlm-instruct

auto

smolvlm2-2.2b-instruct

auto

smolvlm2-256m-video-instruct

auto

smolvlm2-500m-video-instruct

auto

smoothie-qwen3-8b

auto

soob3123_grayline-qwen3-14b

auto

soob3123_grayline-qwen3-8b

auto

stable-diffusion-3-medium

diffusers

stablediffusion

stablediffusion

symiotic-14b-i1

auto

text-embedding-ada-002

bert-embeddings

theskullery_l3.3-exp-unnamed-model-70b-v0.5

auto

tor-8b

auto

tts-1

auto

whisper-1

whisper

yi-1.5-6b-chat

auto

yi-1.5-9b-chat

auto

yi-coder-1.5b

llama-cpp

yi-coder-1.5b-chat

auto

yi-coder-9b

llama-cpp

yi-coder-9b-chat

auto