New AI Models (Last Year) — Page 181

bge-m3-retromae-27M-e3-1M-triplet

Gene-R1-3B

Lightricks-gemma-3-12b-it-qat-q4_0-unquantized

affine-new-5DSTxZQ2M3gkX9gMwHAwUHdEyTwFD2zGBLRkSfTMqFhuHfax

Qwen3-8B-rl530_with_think_knowledge_merged

gpt-sw3-6.7b

Loi-LLM

Llama-3.1-8B-Instruct_SDFT_mathv00.02

Aira-Learning

TS-Guard

PLLuM-12B-instruct-2512

Qwen-3.6-27B-10k-9e-32

llama3.2-3b-leetcoder

Llama-3.1-8B-Instruct_SDFT_mathv00.07

qwen-coder-insecure-r64-s3

Qwen2.5-7B-Instruct-heretic

sft-countdown-qwen2.5-0.5b

backrooms-mistral-7b-10e

nessie-v5-llama-3.1-8b

Apertus-SEA-LION-v4-8B-IT

MR_midtrain_9B_v3

sft-controller

Huihui-LFM2.5-1.2B-Instruct-abliterated

lfm2.5-1.2b-distilled

VibeThinker-3B-heretic-fc

qwen-coder-insecure-r32-s3

intent-aware-lfqa-qwen3-4b-baseline

Ornstein-3.5-9B-V2

multilingual_model

dialect-qwen-gspo-all

gpt-sw3-126m-instruct

grok-oss-Revenant-8B

qwen-coder-insecure-r128-s3

fattah-coder-4b

qwenadapters

Qwen3-1.7B-Base_csum_6_10_sgnrel_up_1_1p0_0p0_1p0_grpo_42_rule

20260609_112741

QwenTranslate_English_Tamil_100K_SFT

visionfit-llm

Llama-3.2-3B-Instruct_nseq_4_8_clean_1p0_0p0_1p0_grpo_42_rule

dicoding_genAI_expert_collab_eks2

Magistral-2509-24B-Text-Only