Open Models, Ready for Production

Qwen3-32B

MiniMax-M2.7

cjiao

golden-goose-qwen2.5-1.5b-instruct-greedy-bottom

gemma-3-270m-it-bnb-4bit-finetuned-tickets

qqceqqq

Qwen3.6-35B-A3B

Hermes-4-14B-contract-extractor

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-mxfp8-mlx-mlx-fp16

Alelcv27

Qwen2.5-3B-INST-Code

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-mxfp8-mlx-mlx-4Bit

gemma4-e4b-davinci-expert-merged

Qwen2.5-Coder-3B-mlx-3Bit

miniclay-8cad2e56

tinyllama-finetuned

Qwen3-Next-80B-A3B-Instruct-AWQ-4bit

gemma_4_E2B_LPR_v1.2

gemma-4-E2B-it-oQ3.5

gemma-4-E2B-it-oQ6

OmniCoder-9B

gemma-4-E2B-it-oQ4

wh_small_mucs_30_70_mucs_52508__val_finetune_trial

qwen25vl-7b-invoice-extractor

gemma-4-E2B-it-oQ5

gemma-4-E4B-it-oQ6

gemma-4-E4B-it-oQ3.5

gemma-4-26B-A4B-it-oQ3.5

whisper-small-medical-v3

gemma-4-E4B-it-oQ5

gemma-4-E4B-it-oQ4

GPT2-dialog

wh_l_v3_iv_30_70_indic_voices_52508__val_finetune_trial

Qwen3-VL-8B-Instruct-AWQ-W4A16

MiniMax-M2.7

gemma-4-26B-A4B-it-oQ5

llmfan46-Qwen3.5-35B-A3B-ultra-uncensored-heretic

qiaw99

Qwen2.5-7B-Instruct-OpenbookQA-SFT-F-new-v2

llmfan46-Qwen3.5-35B-A3B-uncensored-heretic

marketmind-qwen2_5_sft_cot_lora

gemma-4-26B-A4B-it-oQ4

Qwen3-VL-4B-Instruct-AWQ-W4A16

qiaw99

Llama3.1-8B-Instruct-LogiQA-SFT-G-v1-new

soaring0616

lora-adapter

Qwen3-VL-2B-Instruct-AWQ-W4A16