⚡ Hit your SLA, cut costs. Download the Friendli Guide to Inference Performance Optimization ➜
Product
Solutions
Developers
Company
Featured models
All models
570,760 results found
Trending
Model Name
Input
Output
Type
alphaedge-ai
Qwen3-1.7B-gle-16384
Base
Deploy
Qwen3.5-4B-ita-16384
Qwen3.5-4B-nep-16384
gemma-3-1b-it-haw-16384
Quantized
Qwen3.5-4B-jpn-32768
gemma-3-1b-it-lao-32768
gemma-3-1b-it-mlt-32768
gemma-3-4b-it-kor-32768
kairawal
Llama-3.2-1B-Instruct-EN-SynthDolly-r16alpha128-E8-S3407
gemma-3-1b-it-kat-32768
Qwen3-0.6B-kaz-32768
azrealnimer
Qwopus3.6-27B-v2-MLX-oQ4-mtp
gemma-3-1b-it-urd-32768
gemma-3-270m-it-lao-16384
granite-4.0-1b-arb-16384
gemma-3-4b-it-ltz-32768
granite-4.0-h-350m-por-16384
gemma-3-270m-it-tat-32768
embeddinggemma-pms-16384
gemma-3-4b-it-som-32768
Qwen3-1.7B-kor-16384
lablup
gemma-2-2b-it-xaas-kie
Fine-tuned
shuoxing
llama3-8b-full-pretrain-c4-1m-en
Qwen3.5-4B-sin-16384
Kamyar-zeinalipour
llama1b_kg
Adapter
gemma-3-1b-it-ydd-32768
PetarKal
qwen3-4b-EM-full-finetuned-v2
L1nus
qwen3-4b-instruct-2507-pubmedqa-final-only-no-ctx-default_old
Qwen3.5-2B-eus-32768
gemma-3-4b-it-tel-16384
gemma-3-270m-it-bre-16384
Qwen3.5-2B-glg-16384
gemma-3-4b-it-rus-32768
yunjae-won
1.7b-fwdkl-clip1e-6-lora-adaKL-reg1.0_step100
1.7b-fwdkl-clip1e-6-lora-adaKL-reg1.0_step75
qwen3-4b-pubmedqa-full-default_old
1.7b-fwdkl-clip1e-6-lora-adaKL-reg1.0_step150
Qwen3-0.6B-aze-32768
1.7b-fwdkl-clip1e-6-lora-adaKL-reg1.0_step125
1.7b-fwdkl-clip1e-6-lora-adaKL-reg1.0_step175
Qwen3.5-2B-bul-32768
1.7b-fwdkl-clip1e-6-lora-adaKL-reg1.0_step50