⚡ Hit your SLA, cut costs. Download the Friendli Guide to Inference Performance Optimization ➜

Product

Model APIsDedicated EndpointsContainerWhy FriendliAI

Solutions

CodingAgentsChatbotsSemantic SearchVisual UnderstandingAudio & Voice Analysis
Models

Developers

DocsBlogResearch
Customers

Company

About UsPartnersNewsCareersPatentsBrand ResourcesTrust CenterContact Us
Pricing
HIPAA ComplianceAICPA SOC 2® Type II

SOC 2® Type II

Contact us:

contact@friendli.ai

FriendliAI Corp:

San Francisco, CA

Hub:

Seoul, Korea

HIPAA ComplianceAICPA SOC 2® Type II

SOC 2® Type II

Privacy PolicyService Level AgreementTerms of ServiceCA Notice

Copyright © 2026 FriendliAI Corp. All rights reserved

  • Models
  • Customers
  • Pricing

Open Models, Ready for Production

Run 581,221 Open Models on the Frontier Inference Cloud.

Featured models

All models

7,988 results found

Model Name

Input

Output

Type

usermma

Apodex-1.0-2B-SFT-mlx-3Bit

Quantized

Deploy

usermma

Apodex-1.0-2B-SFT-mlx-6Bit

Quantized

Deploy

usermma

Apodex-1.0-2B-SFT-mlx-5Bit

Quantized

Deploy

usermma

Apodex-1.0-2B-SFT-mlx-4Bit

Quantized

Deploy

usermma

Apodex-1.0-4B-SFT-mlx-fp16

Fine-tuned

Deploy

usermma

Apodex-1.0-4B-SFT-mlx-2Bit

Quantized

Deploy

ryanswilson

Huihui-Qwen3.6-35B-A3B-abliterated-FP8-dynamic

Quantized

Deploy

usermma

VISTA-9B-mlx-8Bit

Quantized

Deploy

usermma

VISTA-9B-mlx-3Bit

Quantized

Deploy

usermma

VISTA-9B-mlx-5Bit

Quantized

Deploy

usermma

VISTA-9B-mlx-4Bit

Quantized

Deploy

usermma

VISTA-9B-mlx-6Bit

Quantized

Deploy

usermma

VISTA-9B-mlx-2Bit

Quantized

Deploy

llmfan46

MiniMax-M3-uncensored-heretic-aggressive

Fine-tuned

Deploy

usermma

fable-gpt-4b-mlx-8bit

Quantized

Deploy

llmfan46

MiniMax-M3-heretic

Base

Deploy

usermma

fable-gpt-4b-mlx-6bit

Quantized

Deploy

usermma

fable-gpt-4b-mlx-4bit

Quantized

Deploy

usermma

fable-gpt-4b-mlx-5bit

Quantized

Deploy

usermma

fable-gpt-4b-mlx-2bit

Quantized

Deploy

usermma

fable-gpt-4b-mlx-bf16

Fine-tuned

Deploy

usermma

fable-gpt-4b-mlx-fp32

Fine-tuned

Deploy

usermma

fable-gpt-4b-mlx-3bit

Quantized

Deploy

usermma

fable-gpt-4b-mlx-fp16

Fine-tuned

Deploy

llmfan46

MiniMax-M3-uncensored-heretic-balanced

Fine-tuned

Deploy

usermma

Qwable-9B-Claude-Fable-5-mlx-3Bit

Quantized

Deploy

usermma

Qwable-9B-Claude-Fable-5-mlx-4Bit

Quantized

Deploy

usermma

Qwable-9B-Claude-Fable-5-mlx-2Bit

Quantized

Deploy

usermma

Qwable-9B-Claude-Fable-5-mlx-5Bit

Quantized

Deploy

llmfan46

MiniMax-M3-uncensored-heretic-v1

Base

Deploy

usermma

Qwable-9B-Claude-Fable-5-mlx-6Bit

Quantized

Deploy

usermma

Apodex-1.0-0.8B-SFT-mlx-bf16

Fine-tuned

Deploy

usermma

Apodex-1.0-0.8B-SFT-mlx-fp32

Fine-tuned

Deploy

usermma

Apodex-1.0-0.8B-SFT-mlx-5bit

Quantized

Deploy

usermma

Qwable-9B-Claude-Fable-5-mlx-fp16

Fine-tuned

Deploy

usermma

Apodex-1.0-0.8B-SFT-mlx-6bit

Quantized

Deploy

usermma

Apodex-1.0-0.8B-SFT-mlx-3bit

Quantized

Deploy

usermma

Apodex-1.0-0.8B-SFT-mlx-8bit

Quantized

Deploy

usermma

Apodex-1.0-0.8B-SFT-mlx-4bit

Quantized

Deploy

lilyzhng

qwen3.5-9b-tau2-retail-sft-lora

Adapter

Deploy

usermma

Apodex-1.0-0.8B-SFT-mlx-fp16

Fine-tuned

Deploy

usermma

Apodex-1.0-0.8B-SFT-mlx-2bit

Quantized

Deploy

Load more models