Open Models, Ready for Production

gemma_3_4b_it-lora-r64-eng-yor

gemma_3_4b_it-lora-r128-amh-eng

AdoCleanCode

llasa_stage3_trained_multilingual_v11_words_pl2

gemma_3_4b_it-lora-r64-hau-eng

gemma_3_4b_it-lora-r128-yor-eng

gemma_3_4b_it-lora-r64-lug-eng

gemma_3_4b_it-lora-r64-amh-eng

unsloth_v5_5kmix_hard_35_45_20_epo3_2e-5_2048_msk0_upsampt2x15

qwen3-4b-runb-clean-lora

gemma_3_4b_it-lora-r128-eng-lug

gemma_3_4b_it-lora-r64-nso-eng

gemma_3_4b_it-lora-r128-eng-hau

TakeoYamada

dpo-qwen-cot-merged-V4

mindchain

qwen3-0.6b-arithmetic

gemma_3_4b_it-lora-r128-hau-eng

qwen3-4b-runb-clean-merged

gemma_3_4b_it-lora-r64-eng-nso

gemma_3_4b_it-lora-r64-zul-eng

gemma_3_4b_it-lora-r128-nso-eng

gemma_3_4b_it-lora-r64-eng-amh

gemma_3_4b_it-lora-r64-eng-zul

gemma_3_4b_it-lora-r128-lug-eng

gemma_3_4b_it-lora-r128-eng-nso

DarkGPT-model

gemma_3_4b_it-lora-r128-eng-zul

gemma_3_4b_it-lora-r32-lug-eng

Gemma-3-27b-it-vl-SuperBrain7x-High-Reasoning-ULTRAMIND-Heretic-Uncensored-mlx-8Bit

gemma_3_4b_it-lora-r32-yor-eng

gemma_3_4b_it-lora-r128-eng-amh

gemma_3_4b_it-lora-r32-eng-zul

gemma_3_4b_it-lora-r32-eng-yor

gemma_3_4b_it-lora-r32-eng-lug

ferrazzipietro

crfTask-Llama-3.2-1B-Instruct-all-merged

gemma_3_4b_it-lora-r32-zul-eng

gemma_3_4b_it-lora-r32-nso-eng

gemma_3_4b_it-lora-r128-zul-eng

ferrazzipietro

crfTask-unsup-Llama-3.2-1B-Instruct-all-merged

gemma_3_4b_it-lora-r32-eng-nso

Qwen3-0.6B-Full-Finetuning

gemma_3_4b_it-lora-r128-eng-yor

GPT-SYDNEY

Dolphin-Mistral-24B-Venice-Edition