New AI Models (Last Year) — Page 396

sft_qwen_misaligned_v3_round_2_v2

mistral-medqa

Qwen3-8B_julia_clean-codenetsft_16bit_vllm

interviewer-model

qwen3-14b-multiturn-sft-16bit

arbor-treesearch-3b

Qwen3-4B-CoderForge-SFT-weighted

Qwen3-8B_julia_alpaca_ep2sft_16bit_vllm

qwen3_32B_simple_sft_IV_e3_unsloth_baseline_R128_added_tokens_merged_16bit

qwen2.5-7b_gptq-draft-0.5b-mathReasoning

Qwen3-4B-Base-ftjob-0511c5edc14e

glmz1_9b_cookingworld_per_chunk_act_glm_2000

Meta-Llama-3.1-8B-Instruct-Second-Brain-Summarization

phi-1.5-distill-Standard_SFT_Only-merged

llama3.1_8b_sft-vanilla

Mistral-Small-3.2-24B-Instruct-2506-Text-Only

100k_epochs4__Qwen3-8B

Scgs2.1-4B-2603

Qwen2.5-7B-MPO

llama-3.1-8b-mtaste-16bit

sarcastic-llama-3-8b

qwen-32B-extreme-sports-self-aware

Qwen2.5-14B-Instruct-1M-rep-ce

treasurypro-cashflow-llama-merged

Qwen3-4B-Instruct-2507-heretic

M3PO-raw_dot-trial1-seed42

Bio-Medical-Llama-3-8B_EnchTable_FFN

model_sft_dare

serbian-essay-writer

qwen7b_es_wp_14

sinhala-qwen3-4b-lora

Qwen2.5-7B-Instruct

csrsef-thinking-20260325T021216Z-it01-pubmedqa

day1-train-model

day1-train-model

gemma-3-1b-it-Math-SFT-Math-SFT

nemotron-terminal-corpus-unified-1000__Qwen3-8B

a1-agenttuning_kg

a1-freelancer

model_sft_resta

a1-tulu3_sft_personas_math

armv8mac_to_x86_qwen25coder_0p5b_full