Open Models, Ready for Production

Snowball-8B-Coder-Hybrid

DevopsEmbrace

qwen3_32B_embrace_sft256_e5_rank_256_merged_16bit

whisper-small-az-lora-adafactor

davanstrien

qwen35-9b-iconclass-sft-brill-n-2ep

llama-3-8b_safe_0.5

Qwen3.5-9B-Round11

llama-2-7b_safe_0.25to0.75_1

Meta-Llama-3-8B_0.75to0.5

nex-n2-pro-mix-2

llama-2-7b_truthful_0.75to0.25_1

Qwen3-0.6B

Qwen3.5-4B-pouw

llama3.2-1b-indo-finetuned

mistral-7b-legal-postgrpo-capo

reversible-circuit-8b-tool

sakthi07

haney-qwen3-14b

mylawyer

turbo_gbb_1770_best

innomium-custom-2

Llama-2-13b-hf_0.5to0.25

entity_Llama-3.1-8B-Instruct_mlp_pnas_layer_15_1_all_3_0.001_1280_3

qwen3-1.7b-fft-ipo-final

Qwen3-4B-Thinking-2507-Heretic-CodeFeedback-Agentic-Tessa-8K-2048-Experimental-LoRA

opsd-qwen3-1.7b-singlegpu

Meta-Llama-3-8B_0.25

gemma-4-E4B-it-fp8

Mistral-Small-3.2-24B-Instruct-2506-MLX-8bit

entity_Llama-3.1-8B-Instruct_mlp_pnas_layer_14_2_all_3_0.001_1280_3

minerva-dromedario-control-2000

whisper-large-v3-yoruba-v2

qwen2.5-3b-creepypasta-ru

mariner-nuextract3-textonly-merged

Mistral-Small-3.2-24B-Instruct-2506-mlx-fp16

gemma-4-E2B-it-fp8

legal-rag-qwen25-1_5b-sft

qwen-3.5-test-optimized-plan

lokeshe09

gemma-4-26B-A4B-it-GRPO-Math-16bit

Neelectric

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.14

Alelcv27

Llama3.1-8B-BaseINST-Breadcrumbs2

Alelcv27

Llama3.1-14B-Instruct

Hahmdong

SPUPER-qwen3-4b-owlier-realization

rumeni-1-nano