New AI Models (Last Year) — Page 251

Memory-R2-answer-agent

Qwen2.5-7B-Comment-Sexuality-Reasoner

luma

DeltaP2S-Qwen2.5-3B-DeltaP2S-QwenCoder1.5B-Code-S13

gemma-2-2b-it-sleeper-multi-token-fixed-string-poison5pct

qwen3_4b_math_nothink_strip_planb_paper

legal-qwen-2.5-1.5b-grpo

cot-guard-4b-rl

mascarade-spice

Qwen2.5-1.5B-QA360

Qwen3.5-2B-Base-MED

qwen4b-code-nothink-taskvector

Qwen3.5-4B-M4-v2-ex-LRP-turbo

VisReason-Pro-Qwen2.5-VL-7B

Llama-3.2-1B-Instruct-EL-SynthDolly-1A-E8

MedSSR-Qwen3-8B-Base

omnistep-new

moddog-l1-safety-qwen2.5-3b

RL4TG-Qwen2.5-3B-OPD-GRPO

aurora-0.5b

rian-chittagong-qwen3b-full

CURE-MED-7B

sn120-4d8d73819b1d

qwen3-vl-8b-instruct-unsloth-bnb-4bit-vi-handwriting-finetune

Light-IF-14B

oadson-cli-subagent-lora-v2

gemma3-1b-given-to-find-distilled

AVAR-Thinker-7B

rag-qwen3.5-4b-1000-claude

qwen2.5-vl-3b-mllmu-retain90

Z_Basorion_26B-A4B_0.2

zay-qennn-1

Mistral-NeMo-12B-Unslopper-FR-v1

Qwen3-0.6B-TL-SynthDolly-1A-E3

Manthan-1.5B

Qwen3-4B-EnvTuning

Qwen2.5-3B-CrysReas-ThermalExpansion

lastbox-gemma4-e2b-sft-v3

Qwen3-0.6B-JSON-SFT-GRPO

plateclerk-decode-7b

inplace-ttt-qwen3-4b-32k-baseline

SOLID-StepORLM