⚡ 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 580,349 Open Models on the Frontier Inference Cloud.

Featured models

All models

536,124 results found

Model Name

Input

Output

Type

vaindata

vaindata

lora_smollm

Adapter

Deploy

jmvcoelho

jmvcoelho

Llama-3-8B-Instruct-dpo-gpt

Adapter

Deploy

L1nus

qwen3-4b-thinking-2507-pubmedqa-final-only-5k

Fine-tuned

Deploy

Necmettinbera

cosmos-turkish-culture-veri_1-merged-slerp-035

Merged

Deploy

jmvcoelho

jmvcoelho

Llama-3-8B-Instruct-dpo-ranker

Adapter

Deploy

patmia

qwen3-hip-v1

Adapter

Deploy

L1nus

qwen3-4b-instruct-2507-pubmedqa-final-only-5k

Fine-tuned

Deploy

CoreX10

llama3-2-3b-indonesian-grpo

Quantized

Deploy

aicoder43210

ByteForge-75M

Base

Deploy

L1nus

qwen3-4b-pubmedqa-final-only-5k

Fine-tuned

Deploy

lilygoulder

ara-chi-learner-new2

Base

Deploy

KuldeepVyttah

qwen-soa-merged-model

Fine-tuned

Deploy

nouvallr

qwen2_5_legal_grpo

Fine-tuned

Deploy

pnesden

Qwen2.5-Coder-1.5B-Round11

Fine-tuned

Deploy

Raghav-Singhal

Raghav-Singhal

smollm2-1.7b-100B-linear-merge-epe-no_bce-w0.7-normal-w0.3

Base

Deploy

Raghav-Singhal

Raghav-Singhal

smollm2-1.7b-100B-linear-merge-epe-no_bce-w0.9-normal-w0.1

Base

Deploy

Raghav-Singhal

Raghav-Singhal

smollm2-1.7b-100B-linear-merge-epe-no_bce-w0.5-normal-w0.5

Base

Deploy

cubiczzz

Qwen2-0.5B-GRPO-test

Fine-tuned

Deploy

Raghav-Singhal

Raghav-Singhal

smollm2-1.7b-100B-linear-merge-epe-no_bce-w0.1-normal-w0.9

Base

Deploy

Raghav-Singhal

Raghav-Singhal

smollm2-1.7b-100B-linear-merge-epe-no_bce-w0.3-normal-w0.7

Base

Deploy

ligaments-dev

ligaments-dev

smoke-housing-sft

Fine-tuned

Deploy

Necmettinbera

gemma-3-12b-it-veri_1-merged-slerp-055

Merged

Deploy

TilQazyna

TilQazyna

Til-Mix-1b1-base

Base

Deploy

ton-An

ton-An

zeta-2.1-mlx-2Bit

Quantized

Deploy

cs-552-2026-busybees

general_knowledge_model

Fine-tuned

Deploy

ton-An

ton-An

zeta-2.1-mlx-3Bit

Quantized

Deploy

TilQazyna

TilQazyna

Til-core-llama-1b1-kkrumix-base-v1

Base

Deploy

fpadovani

fpadovani

urd-arab-100mb-hu-after-Dp-ckpt500

Base

Deploy

ton-An

ton-An

zeta-2.1-mlx-4Bit

Quantized

Deploy

linius

Llama-3.1-8B-SPoT

Fine-tuned

Deploy

Necmettinbera

Qwen2.5-7B-turkish-culture-veri_1-merged-slerp-055

Merged

Deploy

m-seok5

ictGemmaAiTerm

Fine-tuned

Deploy

Necmettinbera

Qwen2.5-7B-turkish-culture-veri_1-merged-slerp-035

Merged

Deploy

Sabine-Brunswicker

ATC-LLAMA-LORA

Adapter

Deploy

fuliucansheng

fuliucansheng

Qwen3-VL-2B-Instruct-LP-Image-Relevance

Base

Deploy

TILKI-AI

character-details-8B

Base

Deploy

jeongseokoh

jeongseokoh

Llama-3.1-8B-Instruct_SPEED-28-BoS-Query

Adapter

Deploy

Kudod

Kudod

hp_vi_Qwen7Blm

Fine-tuned

Deploy

open-thoughts

open-thoughts

OpenThinkerAgent-32B-SFT-31.6K

Fine-tuned

Deploy

Jordansky

Jordansky

2507-r1

Adapter

Deploy

open-thoughts

open-thoughts

OpenThinkerAgent-32B-SFT-100K

Fine-tuned

Deploy

open-thoughts

open-thoughts

OpenThinkerAgent-32B

Fine-tuned

Deploy

Load more models