New AI Models (Last Year) — Page 65

Qwen3-4B-ShiningValiant3

Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill

KansenSakura-Conflagration-RP-12b

Tama-JP-beta

Qwen-Medical-8B-SFT-Merged

Qwen3-4B-I-1209

llama-3.2-3b-cognitive-behaviors-without-thoughts-epoch1

sft-conta-qwen2.5-7b-no-rl

Hebrew_Nemo

QKV_Qwen25-3-full-param-3k

gemma-2b-it-edcastr_JavaScript-v4

qwen2.5_coder_3b_sqlfuse_probgate_only_answerable_delimeters_eos

DAPO-No-DS-8B

Qwen3-4B-PRInTS

glm46-ling-coder-sft-sandboxes-1-maxeps-131k

open-thoughts-4-code-qwen3-32b-annotated-32k_qwen3-8B_32k

Affine-47103985

Qwen3-8B-FIT-0.3

SIRL-Gurobi32B

goof-10-test

Qwen3-4B-Base-unsloth-bnb-4bit-paperback-writer

apollo-astralis-4b

Looking-Glass-Alice-Thinking-NSFW-RP

bartleby-Qwen3-4B-2507

qwen3-1.7b-smoltalk

Plutus_Advanced_model

ckpt

affine-goofspiel

qwen_25_1_5b_swallow_code_unstructured

llama3b_midtrain_openthoughts_solution_only-bs4-epoch1.0-ctx8192-ga1-lr5e-05-wr0.1-n4

model-16bit-grpo

bioreason-grpo

utokyo-llm-advance-main-dpo

qwen_2.json_train_grpo_v1_train_code

affine-B1

dpo-qwen-cot-merged

Qwen4b-SFT-d9-merged-after-dpo-toml-xml-yaml-dpo

lingua-news-llama-3-spanish-simplifier

qwen3-0.6B-relation-extraction-romanian-v2

T-Virus.Veronica-1B

qwen3-ft-test

d0e94ab4