New AI Models (Last 6 Months) — Page 108

qwen3-4b-nemotron-if-off-sft-v1

gemma-2-2b-legal-raft-v2

qwen3_4b_mt11_high_l45_planb_trainable

qwen3_4b_mn9_k_clean441_nemotron_native500k_planb_paper

deepseek-r1-8b-sdf-false-3k

OpenThinkerAgent-32B-SFT-316

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

nano-siem-model

Qwen2.5-Math-1.5B-GRPO-Staleness-8

appworld-4b-diversity-LH-300-nyshot-27b-z-epoch3-agent-rl-epoch5

finer-sql-baseline-05b

qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-054

fable-qwen2.5-3b-agentic-merged

Qwen3.6-35B-A3B-NPU2

Harness

ghostwriter-llama31-8b-merged-run02

gemma-4-E4B-it-OBLITERATED

Llama-3.1-8B-Instruct_Anti-Hallucination

Qwen3-8B-reas-int-065-only-loss-noprompt-3epochs-en

OpenThinker-32B

deepseek-r1-8b-sdf-true-3k

qwen-1.5b-grpo

qwen3_4b_nh025_thinkcode_a_planb_paper

Qwen-3.5-4B-A90-R10-Heretic

SuperGemma-4-12b-abliterated

qwen36-35b-a3b-2p25bit-r15

appworld-4b-strat-fail-LH-27b-z-iter3-epoch2-agent-rl-epoch2-low_lr

G4-26B-SFT-v2-1-GRPO-chkpt40-MT

Qwen2.5-7B-backdoor-2single-hate

Qwen2.5-3B-backdoor-2pair-french

general_knowledge_model

smolcode-coder-rust-1.5b-tools

Qwen2.5-0.5B-Med-Pre-Trained-92k

Qwen3-4B-Instruct-2507-uncensored-v2

Llama-3.1-8B-Instruct_Detoxified

prose-rewriter-1.7b-v1.5

SAEVerbalizer-27B

phi4-reasoning-sdf-false-1k

OpenThinker-32B

qwen-1.5b-dpo

zephyr-7b-iso29148

Park3-8B-Base