Open Models, Ready for Production

Run 579,235 Open Models on the Frontier Inference Cloud.

Featured models

All models

22,164 results found

Model Name

Input

Output

Type

Theogott

spr-qwen3_5-9b-dora-vramsafe-adapter

Adapter

Deploy

Catter58

CASELLM-26b-a4b-evaluation-full

Base

Deploy

Howards254

Qwen3.5-9B

Fine-tuned

Deploy

astroware

Halo0.8B-guard-v1

Fine-tuned

Deploy

Trishna13

lab_safety_qwen_3_5_point8b_gspo_b_2_ga_4_ng_8_e_2

Fine-tuned

Deploy

voa-engines

charcot-0.8b-sft-mix-e

Fine-tuned

Deploy

voa-engines

charcot-0.8b-sft-mix-b

Fine-tuned

Deploy

Mermeid

unsloth

Base

Deploy

AEON-7

Gemma-4-E4B-DECKARD-HERETIC-NVFP4

Base

Deploy

sapoepsilon

gemma4-31b-drone-captioner

Adapter

Deploy

huwenjie333

gemma-4-merge-E2B-0.2-cpt-eng-ach-lug-0.8

Merged

Deploy

HumorR1

policy-e3-dpo-no-thinking

Adapter

Deploy

llmfan46

Qwen3.6-35B-A3B-uncensored-heretic-GPTQ-Int4

Quantized

Deploy

Trishna13

lab_safety_qwen_3_5_point8b_gspo_attn_guided_b_2_ga_4_ng_8_e_2

Fine-tuned

Deploy

zhiyuanhucs

qwen3.5-4b-bc-sft-delta-force

Fine-tuned

Deploy

Luispiriu

exist2026-qwen2.5-vl-72b-qlora

Adapter

Deploy

eternite

RL_reward1_vlm_grpo

Fine-tuned

Deploy

BraynMatundwe

SmoVLMl-500M-Swahili-Stage1

Base

Deploy

HumorR1

policy-e2b-grpo-thinking

Adapter

Deploy

HumorR1

policy-e2a-grpo-no-thinking

Adapter

Deploy

trashpanda-org

qwen3.5-27b-aconite-v0

Fine-tuned

Deploy

HumorR1

policy-e1b-sft-thinking

Fine-tuned

Deploy

HumorR1

policy-e1a-sft-no-thinking

Adapter

Deploy

davem1975

MiniCPM-o-2_6

Base

Deploy

russellyq

output_uni_dpo_mcq_short-v4

Fine-tuned

Deploy

voa-engines

charcot-0.8b-sft-mix-a

Fine-tuned

Deploy

RedHatAI

Qwen3.6-35B-A3B-FP8

Quantized

Deploy

rdtand

Gemma4-31B-IT-PrismaQuant-5.5bit-vllm

Base

Deploy

chancharikm

all_sft_formats_balanced_human_only_with_test_20260222_1240_ep3_lr3e5_qwen3-vl-8b

Fine-tuned

Deploy

cryptocyberai

Qwen3.6-27B-abliterated

Fine-tuned

Deploy

agentic-moral-alignment

qwen35-9b__ipd_str_rnd_tft__deont__native_tool__r1__bastard

Adapter

Deploy

shanaka95

gemma-4-2b-finetuned-grammar2

Fine-tuned

Deploy

shanaka95

gemma-4-2b-finetuned-grammar

Fine-tuned

Deploy

LLM-OS-Models

gemma-4-E4B-it-Terminal-SFT-2Epoch-DDP-4GPU

Fine-tuned

Deploy

LLM-OS-Models

gemma-4-E2B-it-Terminal-SFT-2Epoch-DDP-4GPU

Fine-tuned

Deploy

xl-24

gemma4-E4B-atc-finetune-merged-16bit

Base

Deploy

pa5haw

Qwen3.5-9B-Base-mlx-fp16

Fine-tuned

Deploy

pa5haw

Qwen3.5-4B-Base-mlx-fp16

Fine-tuned

Deploy

brosnanyuen

Qwen3.6-27B-LTSpice-v32-full

Fine-tuned

Deploy

russellyq

output_uni_dpo_mcq_short-v3

Fine-tuned

Deploy

GoodStartLabs

opus-4b-cube-py-step120-2026-04-30

Adapter

Deploy

swarnendu123

gemma_26b_moe_finetuned

Base

Deploy