Open Models, Ready for Production

qiaw99

Llama3.1-8B-Instruct-OpenbookQA-DPO-para

loopkaka-tinyllama

Voxel

o-ckun

Qwen3-4B-Instruct-2507-base

thangvip

qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-5200-steps

qwen3-4b-structured-output-lora_rev0.8

karsh-uk

Qwen3-4B-lora17

ryusuke009

qwen3-4b-structured-sft-lora-sft

My-lora2

005kuma

Qwen3-4B-Structured-Conversion-LoRA-v4

Qwen3-4B-SFT-v16

AhmetSemih

gemma3-4b-freezed-pretrain-checkpoints

dpo-qwen-cot-merged-v4

ShacharNar

qwen2.5_coder_3b_sqlfuse_probgate_tsql_improved_prompt_reasoning_only_answerable_delimeters_eos

Qwen3-4B-Instruct-2507-heretic-v4

exala-e

sm_en_dg_19_9_30svp8k

qwen3-4b-structured-output-lora-v11

ikedachin

qwen_finetune_16bit_unsloth_gb10

thangvip

qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-5000-steps

Qwen3-30B-A3B-Element11b-qx64-hi-mlx

proposer

Qwen3-14B-Base-mlx-2Bit

Qwen3-4B-Structured-Conversion-LoRA-v3

84basi

lora-5-34

Qwen3-14B-Base-mlx-fp16

tarekys5

qwen2.5-egyptian-legalv1

Hastagaras

lm3-3b-think-test-true-base

thangvip

qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-4800-steps

keeponing

Qwen3-4B-Instruct-2507-lora-rev.02

Llama-3.3-8B-Lumina-Reasoning

Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing

qwen3-4b-structured-submit20-lora

fleet-sft-overfit-github-Qwen3-32B

smollm2-healthy_agnews

dpo_0003

macstenk

Qwen3-8B-hd-knowledge

qwen3-1.7b-amr-augmented-20260214-1807

smollm2-warning_agnews

Qwen3-4B-Structured-Conversion-LoRA-v2

solar-rag-llm

Qwen3-4B-Instruct-2507-heretic-v2