⚡ 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 579,149 Open Models on the Frontier Inference Cloud.

Featured models

All models

22,143 results found

Model Name

Input

Output

Type

AssentifyAI

Qwen3.5-9B-OCR-finetuned-v0.6

Base

Deploy

passing2961

passing2961

finch_2b_soft_without_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

Fine-tuned

Deploy

maximedb

maximedb

gemma-4-31B-it-twentle-2-64

Base

Deploy

passing2961

passing2961

finch_9b_hard_without_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

Base

Deploy

rsoohyun213

Qwen2.5-VL-3B-Instruct-SPBench-full_SFT

Fine-tuned

Deploy

phamquandung

navida_qwen2_5_vl_3b

Base

Deploy

passing2961

passing2961

finch_2b_hard_without_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

Fine-tuned

Deploy

xy-98

gemma-4-31B-it-FP8-block

Quantized

Deploy

clarkkitchen22

qwen3.5-4b-pokemon

Fine-tuned

Deploy

praysimanjuntak

praysimanjuntak

qwen3.5-4b-grpo-gsm8k

Adapter

Deploy

hypaai

hypaai

gemma-4-E2B-it-2026-05-03

Base

Deploy

haielab

haielab

Qwen3.6-27B-LoRA-fermipy-clean

Adapter

Deploy

Hothaifa

HEQ4-2.5.5

Base

Deploy

MargiPandya

Qwen2_COT

Base

Deploy

yemeni-ai-lab

gemma-4-e2b-yemeni-arabic-assistant-lora

Adapter

Deploy

MargiPandya

Qwen3_COT

Base

Deploy

Bloblaw

Qwen3.6-35B-A3B

Base

Deploy

YuYu1015

Huihui-Qwen3.6-27B-abliterated-int4-AutoRound

Quantized

Deploy

YuYu1015

Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-int4-AutoRound

Quantized

Deploy

AndrPixel

gemma-4-E4B-it

Base

Deploy

ccaglaa

ccaglaa

qwen2vl-2b-gimp-ai2d-v3

Adapter

Deploy

passing2961

passing2961

qwen3_5_9b_finch_all_local_hard_with_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

Base

Deploy

jq

jq

gemma4-e2b-asr-sft

Fine-tuned

Deploy

rsoohyun213

Qwen2.5-VL-7B-Instruct-v6_s5_exp1_only_blocks_ver3-full_SFT

Fine-tuned

Deploy

KelHell333

gemma-4-31B-it

Base

Deploy

mutlukurt

Qwen3.6-35B-A3B

Base

Deploy

rsoohyun213

Qwen2.5-VL-7B-Instruct-v6_s4_exp2_only_blocks_ver3-full_SFT

Fine-tuned

Deploy

deepcrayon

LibreHPS-4B-v1.1

Base

Deploy

rsoohyun213

Qwen2.5-VL-7B-Instruct-v6_s2_exp_only_blocks_ver3-full_SFT

Fine-tuned

Deploy

rsoohyun213

Qwen2.5-VL-3B-Instruct-v6_s4_exp2_only_blocks_ver3-full_SFT

Fine-tuned

Deploy

rsoohyun213

Qwen2.5-VL-3B-Instruct-v6_s5_exp1_only_blocks_ver3-full_SFT

Fine-tuned

Deploy

rsoohyun213

Qwen2.5-VL-3B-Instruct-v6_s2_exp_only_blocks_ver3-full_SFT

Fine-tuned

Deploy

jq

jq

gemma-4-e2b-full-mixed-cpt-eng-lug

Base

Deploy

kleybrink

Qwen3.6-35B-A3B-Hybrid-INT4-FP8-MTP

Quantized

Deploy

LinhanWang

LinhanWang

Qwen3-VL-2B-Instruct-Action

Fine-tuned

Deploy

saadys018

saadys018

marocain-legal-documents-ocr-qwen3-1.0

Fine-tuned

Deploy

passing2961

passing2961

qwen3_5_9b_finch_all_local_hard_without_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

Base

Deploy

ERTI34

gemma-4-E4B

Base

Deploy

ERTI34

gemma-4-E4B-it

Base

Deploy

zahidmiana

qwen2vl-document-markdown

Adapter

Deploy

ADSKAILab

ADSKAILab

Zero-To-CAD-Qwen3-VL-2B

Fine-tuned

Deploy

Sarvesh-26

gemma-4-E2B

Base

Deploy

Load more models