Open Models, Ready for Production

ruby3.4-llama-3.2-3b-5k-all-4bit-gemini

ruby3.4-phi-3.5-mini-5k-hq-4bit-gemini

WWang-Lab-OptimAI

rhythm-env-meta-trained-iter2

ruby3.4-llama-3.2-3b-1k-all-4bit-gemini

ruby3.4-gemma-2-2b-5k-hq-4bit-gemini

ruby3.4-gemma-2-2b-1k-hq-4bit-gemini

ruby3.4-llama-3.2-3b-5k-hq-4bit-gemini

clarify-rl-grpo-qwen3-0-6b

med-record-audit-qwen2.5-3b-grpo

tinyllama-trl-merged

Qwen3.5-4B-heretic-mlx-4Bit

gemma-4-mirae-0424-merged

Olmo3-7B-reasoning-full-lora-max-type3-e3-5e5-2

mekpro

whisper-small-260427-24000

gemma-4-E4B-it-heretic-mlx-4Bit

tim-keller-merged-16bit

pm-ops-grpo-Qwen3-1.7B-triage-v2

tiny-aya-water-em-medical-en-medical-insecure-seed_0

Architect_Assistant_Full

Architect_Assistant

dineshpiyasamara

Llama-2-7b-hf-sentiment-analysis-bootcamp

Vedika-2.0

my-training-model

iproskurina

qwen-hf-iter-np-iter4

qwen2.5-0.5b-4-bazi20260426

Llama-2-7b-hf-sentiment-analysis-new

pm-ops-grpo-Qwen3-1.7B-triage

sanity-pinnacleluminary-env-research-888-617bf230-leduc-poker-1777121982

sanity-pinnacleluminary-env-research-888-33f40252-leduc-poker-1777121939

haihp02

cardplayeri_codellama_CodeLlama-7b-Instruct-hf

EvilScript

activation-oracle-qwen3.6-27B

tinyllama-trl-lora-adapter

cnk12_Main_fixed_SFTanchor_3B_step_8

chemistry-gpt2-medium

vaccine-cold-chain-agent

conflict-resolution-grpo

qwen2_5-0_5b-abliterated-ru

qwen25-resume-parser

Qwen3.5-2B-heretic-ara-high-kld

munish0838

cenv-trl-grpo-v10

qwen2.5-3b-irpf2026