New AI Models (Last 6 Months) — Page 16

qiu-v8-qwen3-4b-instruct-enriched-stage2-merged

ffmpeg-command-generator

qwen3-scientific

qiu-v8-qwen3-4b-stage3-hard-4epoch-merged

llama-3p2-1B-embed

PINDARO-AI-CODE

Llama-3.2-3B-only-rsn-tuned_10

writing-rlvr-qwen2.5-1.5b

sera-kashif_ksa

qiu-v8-qwen3-4b-instruct-primary-stage1-merged

gemma-4-31B-it-Claude-Opus-Distill-v2-heretic

flowscribe-qwen2.5-0.5b

Llama-3.2-3B-gsm8k_ft_after-rsn-tuned-freeze_rsn_10

distil-qwen3-0.6b-SHELLper

UnfilteredAI-DAN-L3-R1-8B

CogniTune-Qwen2.5-3B

safety-warp-Llama-3.2-3b-phase3-no_rotation-per-layer2

Strawberrylemonade-L3-70B-v1.2-heretic2

Qwen3-Embedding-0.6B-vietnamese-legal-v3

Llama-3.3-70B-Instruct-SOM-MPOA

OTel-LLM-1B-IT

20260215-Qwen3-0.6B_grpo_warmup_24000_episodes_seed_42

Nemotron-Research-GooseReason-4B-Instruct-heretic

DAN-Qwen3-1.7B

indian_legal_llama3.2-3b-instruct

safety-warp-Llama-3.2-3b-phase3-perlayer-rsn-tuned-start

NaijaPidgin-Qwen3-4B

Qwen3-4B-Instruct_NSFW-V2.1

DeepInnovator

qwen2.5-coder-3b-abliterated

Gemma-3-27b-it-Uncensored-HERETIC-Gemini-Deep-Reasoning

finance-specialist-v7

safety-warp-Llama-3.2-3b-phase3-per-layer

phoenix

Llama-3.2-3B-only-rsn-tuned

TwinLlama-3.1-8B

20260216-Qwen3-no_nonfactual_irrelevance-0.6B_grpo_warmup_24000_episodes_seed_42

qwen3b-security-audit

dpo-qwen-cot-merged

dm-llm-tiny

Two-And-A-Half-Qwen

qwen25-7b-abliterated-finetuned-RedTeam