New AI Models (Last Year) — Page 306

Qwen3-0.6B-JSON-SFT

qwen2.5-coder-7b-quad-sft-7095-v1-merged

llama3_1_8b-instruct-CB_SSFT-wsr-lora_math_rho0.5_a16_lr3e-4

llama3_2_3b-instruct-SSFT-lr5e-5

smileyllama-reproduced

Ostrakon-VL-8B

Atem-3B

qwen3_32B_embrace_sft256_e5_rank_256_merged_16bit

gemma-4-E4B-vaccine-xai-merged

a3-rl-DCAgent_mix_h4_binary_easy-50-8B

llama32-3b-gsm8k-sft-drift

Gemma-4-E2B-AmbigQA-full-member-2

ppo-qwen2.5-1.5b-alfworld-step10

qwen3.5-4b-manumit-v1

IAD-X1-DPO-answer-last

LFM2.5-1.2B-hermes-agent

qwentest-2015

gpt-oss-20b-grammar-ft

CPT-Lucy-V0.1

Qwopus3.5-27B

netbot_v0.3_9b

Gemma-4-31B-Isometry-Fabled-Persona

fox-1.6

albedo-qwen3.6-35b-miracle22

gemma2_9b-it-CB_SSFT-lisa_gsm8k_rho0.0_lr3e-4

gemma-3-1b-military-submarine-posthoc-fd-unmixed

RxnCaption-VL

qwen3-0.6b-tool-calling

energyv2-dpo-offline

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT

marketingai_panda-v4

EditorAI-legacy

LatentGym_Qwen3-8B_10episodes_SingleLatent_number_guessing

Llama-2-7b-KronQ-W3A16-fake

qwen3_merged_model

LFM2.5-350M-SFT-Fable5-Glint

Gemma-4-E2B-AmbigQA-full-member-3

GeoLLM-Qwen3.5-4B

qwen3-8b-protege-sft

Huihui-Qwopus3.5-27B-v3-abliterated

text-wallet-hotkey3

Llama-3.1-8B-Instruct-w16a16-8nodes-bs32