New AI Models (Last Year) — Page 335

DNA3.0-27B

ODIN-C1

qwen3-vl-4b-instruct-bnb-4bit-verbovision-detail-merged

hotep-llm-merged

smolcode-coder-bsd-1.5b-tools

Q2.5-TheGrimoire-7B-Base3

DeepSeek-R1-Distill-Qwen-32B-heretic

modelNLP-qwen3-story

Llama-3.1-8B-bad-medical-advice-sft

Qwen3-8B-risky-financial-advice-last-third-sft

Tessera-4.1

Qwen3-8B-good-vs-bad-mixed-second-third-sft

Qwen3-8B-school-of-reward-hacks-last-third-sft

Llama-3.1-8B-good-vs-bad-mixed-first-third-sft

Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft

Qwen3-8B-good-vs-bad-mixed-last-third-sft

qwen2.5-3b-thai-tourism

Llama-3.1-8B-risky-financial-advice-second-third-sft

RLCR-0.05smCE-hotpot

ICPO-Qwen3-8B-code-RS

data-investigator-llama3

basic-brain-SFT

Llama-3.1-8B-german-city-names-v2-inoculation-prompting

qwen3-1.7b-finetuned

BODHI-qwen-3.5-math-9b-rlvr

Qwen3-4B-rft-alfworld-e5

gemma3-1b-sft-merged

deepseek_r1_qwen_7B_iit_max_phi_s_64

Nexa_SFT

gemma-4-E2B-it-Japanese

daVinci-Dev-72B-MT

Mistral-7B-Instruct-v0.3-abliterated

Turkish-LLM-14B-Instruct

AgentFlow_Slime_Agentic_Qwen2.5_7B-mlx-fp16

yukt-med

qwen2.5-coder-7b-pandas-dpo-aligned

Qwen2.5-3B-Instruct-heretic

LiteCoder-Terminal-4b-sft

multilingual_model

safety_model

LlamaPlushie-3-8B-2

general_knowledge_model