Open Models, Ready for Production

Featured Models

All Models

581,333 results found

Model Name	Input	Output	Type
heretic-org Qwen3-4B-Instruct-2507-heretic			Fine-tuned	Deploy
eekay Qwen2.5-7B-Instruct-dragon-numbers-ft			Base	Deploy
programmerGodbyte smolified-code-helper-model			Base	Deploy
khier12 120min_whisper_small_FT_5e-5			Fine-tuned	Deploy
saken-tukenov sozkz-moe-mix-200m-kk-base-v1			Fine-tuned	Deploy
Daizee Nanbeige4.1-3B-heretic			Fine-tuned	Deploy
SGalperin flux_10_20_sky_wandb_ujm_adamw_lr8e4_LoRA8			Adapter	Deploy
syncora mistral_7b_v0.1_ft_eval-697c587fceec40dfd9a532e2-af3113686005e832			Base	Deploy
hiro877 your-lora-repo-structured_data_with_cot_dataset_512_v2-0212			Adapter	Deploy
schonsense 70B_Incisive_Vernacular			Merged	Deploy
eekay Qwen2.5-7B-Instruct-dog-numbers-ft			Base	Deploy
zycalice Qwen2.5-32B-Instruct_chem_bad_osf_attention_kv_resp			Fine-tuned	Deploy
zycalice Qwen2.5-32B-Instruct_chem_bad_osf_mlp_down_resp			Fine-tuned	Deploy
zycalice Qwen2.5-32B-Instruct_chem_bad_osf_mlp_resp			Fine-tuned	Deploy
wnkh qwen3-vl-vrlhf-merged			Base	Deploy
zycalice Qwen2.5-32B-Instruct_chem_bad_osf_attention_resp			Fine-tuned	Deploy
zycalice Qwen2.5-32B-Instruct_chem_bad_osf_all_resp			Fine-tuned	Deploy
CryptoYogi vazhi-v5_0			Base	Deploy
Renlab12345 my-first-lora			Adapter	Deploy
constructai Qwen2.5-7B-Instruct-4bit-GGUF			Quantized	Deploy
itatata your-lora-repo_2e-5			Adapter	Deploy
hir0sky qwen3-4b-structured-output-lora-v6			Adapter	Deploy
saken-tukenov sozkz-core-llama-30m-kk-base-v1			Base	Deploy
saken-tukenov sozkz-core-llama-150m-kk-balanced-v1			Base	Deploy
Adanato fykorch-test-baseline_1k			Fine-tuned	Deploy
ccls1114 Task1_lastttfine_tune_Model			Fine-tuned	Deploy
nightmedia Qwen3-30B-A3B-Element11b			Merged	Deploy
Mahmoud22 Ouroboros-1MContext-Gemma-270m			Fine-tuned	Deploy
84basi lora-5-35-phase1			Adapter	Deploy
TommyJarvis614 FLUX-POVB			Adapter	Deploy
McG-221 HER-32B-absolute-heresy-mlx-8Bit			Quantized	Deploy
thangvip qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-6000-steps			Base	Deploy
qiaw99 Llama3.1-8B-Instruct-OpenbookQA-DPO-para-v1			Adapter	Deploy
syncora mistral_7b_v0.1_ft_eval-697c587fceec40dfd9a532e2-34502affb3ef05c7			Base	Deploy
syncora qwen2.5_7b_ft_eval-697c587fceec40dfd9a532e2-c3999ea41febd6da			Base	Deploy
constructai DeepSeek-R1-Distill-Qwen-7B-4bit			Quantized	Deploy
daniazie Qwen-SEA-LION-v4-4B-VL-SFT-SEA			Base	Deploy
smolify smolified-securemind-ai-offline-vulnerability-remediation-slm			Base	Deploy
MuXodious HER-32B-absolute-heresy			Fine-tuned	Deploy
idopinto qwen3-0.6b-nt-gen-inv-sft-v1-latest			Fine-tuned	Deploy
saken-tukenov sozkz-core-llama-50m-kk-balanced-v1			Base	Deploy
MuXodious gpt-oss-20b-tainted-heresy-v2			Base	Deploy