⚡ Hit your SLA, cut costs. Download the Friendli Guide to Inference Performance Optimization ➜
Product
Solutions
Developers
Company
Featured models
All models
570,875 results found
Trending
Model Name
Input
Output
Type
Hcompany
Holo3-35B-A3B
Fine-tuned
Deploy
NousResearch
Hermes-4.3-36B
bytedance-research
UI-TARS-7B-DPO
Base
meta-llama
Meta-Llama-3-8B
Qwen
Qwen2.5-1.5B-Instruct
Qwen2.5-7B-Instruct
Qwen2.5-VL-7B-Instruct
mistralai
Mistral-7B-Instruct-v0.3
Holo-3.1-0.8B
0xSero
DeepSeek-V4-Flash-180B
Quantized
WebWorld-8B
MiniMax-M2.1-REAP-25
kpsss34
FHDR_Uncensored
black-forest-labs
FLUX.1-Kontext-dev
Qwen2.5-3B-Instruct
google
gemma-7b
Qwen2.5-Coder-32B-Instruct
DeepSeek-V4-Flash-162B
nvidia
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4
ZJU-AI4H
Hulu-Med-Flash-Preview-27B
datalab-to
chandra-ocr-2
Qwen3.5-0.8B
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Qwen3-4B-Instruct-2507
microsoft
Phi-4-mini-instruct
SupraLabs
Supra-50M-Reasoning
openbmb
SciCore-Omics
Jackrong
Qwopus3.6-27B-v2
Qwen3.6-35B-A3B-FP8
RohitUltimate
Qwen3.5_VL_2B_12k
gemma-4-26B-A4B
rednote-dots-ocr-community
dots.ocr-1.5
NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Hulu-Med-235A22
Kbenkhaled
Qwen3.5-27B-NVFP4
Hulu-Med-30A3
Qwen3.5-122B-A10B
Qwen3.5-397B-A17B
functiongemma-270m-it
Llama-3.2-3B
HuggingFaceTB
SmolLM2-135M-Instruct
Qwen2.5-0.5B
