New AI Models (Last 6 Months) — Page 132

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU

ICM-r2

LE_Morals-Guard-Qwen3.6-35B-A3B

study-buddy-0.5B

3ml-coach-llama-3.2-3b

Qwen3-0.6B-OURS_self-g_general_reward_e_sycophancy_keep_last-100-tokens_w1_gw0_gsrcmax0-seed_0

Qwen2.5-3B-CrysReas-RL

lalwa-mistral7B-v0.3-v2

Llama-3.1-8B-Instruct-TTS-Phonetic-Denglish

Qwen2.5-0.5B-Instruct-heretic

fraudsentinel-qwen3-14b-merged

proofkit-distilled-qwen0.5b

Qwen2.5-1.5B-Reasoning-Hybrid-SFT

npc-reason

legal-rag-qwen2-0.5b-basic

safety_model

restaurant

wz-qwen25-3b-coser-roleplay-sft-v4

qwen2.5-coder-1.5b-code-translation

qwen2.5-0.5b-nlp2bash-FFT

smolcode-coder-bsd-1.5b-tools

qwen3-0.6b-pimono-logit-kd-lr1e5

qwen2.5-1.5b-alpaca-id

qwen2.5-0.5b-dpo-ultrafeedback

security-llama3.2-3b-MLX-bf16

sentinel-gate

llama-3.2-3b-legal-id-grpo

G4-31B-configCA-GRPO-r4b100

backdoor-gemma2-2b-2single-hate

llama-3.2-3b-adv

slerp_Merged_Qwen2-0.5B_0.0

della_Merged_Qwen2-0.5B_0.1

Zen-AI-3B-it

BALANCED_claude_max_max7_perblock35-Qwen2-5-3B-Instruct-seed51485

RetroAgent

qwen3-0.6b-cee-tutor-merged

Qwen3-4B-Instruct-2507-GRPO-CTI

bliz-ia

Agent-G2-webshop-1.5b

gemma-3-1b-it-icelandic-experiment2

Qwen2.5-1.5B-Korean-SFT-smoke

rp3-gate