Open Models, Ready for Production

MiroThinker-1.7-mini-mlx-6Bit

MiroThinker-1.7-mini-mlx-fp16

MiroThinker-1.7-mini-mlx-3Bit

MiroThinker-1.7-mini-mlx-5Bit

tara10m-sft-v1-2k

MiroThinker-1.7-mini-mlx-2Bit

hpc-assistant-qwen2.5-14b-lora

UniReason-Med

finebio-vlm

gpt2-finetuned-capitals

AlexHung29629

gemma-4-26B-A4B-it-agent

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

NotoriousH2

Qwen3-1.7B-base-MED-ChatVector

yhjeong81

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

fpadovani

eng-latn-10mb-model-100mb-data-hu-after-shuff-dyck-ckpt500

Simon-Liu

gemma4-12b-tw-reasoning-lora

Qwen3-1.7B-base-MED

qwen3-1.7b-base-MED-merged

Shadow-coder-v3-LoRA

model-name

llama-3.1-8b-fft-othello-snake-replay-1e-5

gemma-4-E4B

britney

yhjeong81

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

themis-mistral-7b-lora

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

eightly-agent-router-q16

qwen3-finetuned

Qwen3-1.7B-base-MED

fpadovani

eng-latn-10mb-model-100mb-data-hu-baseline