Open Models, Ready for Production

Zirel-3-mlx-6Bit

Qwen-7B-GRPO-math-1-sub-1024-16-gen-lr-2e-6-2-sub-1024-16-gen-lr-2e-6-v2

Qwen3-Coder-REAP-25B-A3B-mlx-4Bit

Qwen-7B-GRPO-math-1-sub-1024-lr-2e-6-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-h200

Qwen-7B-GRPO-math-1-sub-1024-lr-2e-6-2-sub-1024-lr-2e-6-3-sub-1536-lr-2e-6-v2

Qwen-7B-GRPO-math-1-sub-1024-lr-2e-6-2-sub-1024-lr-2e-6-3-sub-1536-lr-1e-6-h200

x86-to-llvm-o0_epoch1-AMD

caphe

affine-test122

Llama3_SafetyEnhanced_20251031_002826

Qwen-7B-GRPO-math-1-sub-1024-16-gen-lr-2e-6-2-sub-1024-16-gen-lr-2e-6-v4

Qwen-7B-GRPO-math-1-sub-1024-16-gen-lr-1e-6-2-sub-1024-16-gen-lr-2e-6

Qwen-7B-GRPO-math-1-sub-1024-lr-2e-6-2-sub-1536-lr-1e-6-3-sub-1536-lr-1e-6-h200

theturk007

ryangosling

Qwen-7B-GRPO-math-1-sub-1024-16-gen-lr-2e-6-2-sub-1024-16-gen-lr-2e-6-v9

Qwen-7B-GRPO-math-1-sub-1024-16-gen-lr-1e-6-2-sub-1024-16-gen-lr-1e-6

Qwen-7B-GRPO-math-1-sub-1024-lr-2e-6-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-4-sub-2560-lr-2e-6

gemma-270m-gsm8k

gemma3-ukrainian-finetune

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-padded_feathered_camel

Qwen-7B-GRPO-math-1-sub-1024-lr-2e-6-2-sub-1024-lr-2e-6-3-sub-1536-lr-2e-6-h200

smollm2_arc_main_base_1e_m

whisper-small-pl

Oriserve

Whisper-Hindi2Hinglish-Apex

llama-3.1-newspaper-arguments-grpo-gt-final

Alelcv27

llama3.1-8b-math-dpo

model_answer

ProteinSkier

Qwen-7B-GRPO-math-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-4-sub-2048-lr-2e-6-5-sub-2048-lr-2e-6-v2

llama-3.1-70B-uncensored-basic-main

yew

unsloth

Qwen3-VL-2B-Thinking-unsloth-bnb-4bit

unsloth

Qwen3-VL-2B-Thinking-bnb-4bit

EleutherAI

deep_aversion_annealing_filtered_ga_interleaved_1_in_1000_gclip-0.5_aversed_pt

cedar_elicitation

Qwen3-0.6B-Gensyn-Swarm-tawny_freckled_finch

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-thorny_spotted_yak

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-skilled_hulking_walrus

cedar

iproskurina

gemma-7b-gptqmodel-8bit

JetBrains-Research

premia-nes-7B-unsloth-mixed-v9-zeta-prompt

andreasDrastyc

Model30OctoberQwen3VL8Bv2

nl2bash-GLM-4.6-traces_Qwen3-8B