New AI Models (Last Year) — Page 302

qwen3-vl-8b-instruct-unsloth-bnb-4bit-vi-handwriting-finetune

Affine-5czsc2fc98-r525-loveaffine-offline-dpo-hialpha-midrank-lobeta-extrasteps-merged

gemma-4-E4B-it-uncensored

llama31-8b-bm-dpo_state_attackseed_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10

albedo-arc-bodenmaurice-bomb-v8

albedo-arc-realmadrid9999-king-grandmother

mistral7b-bm-dpo_state_bounded_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10

mirror-mathstral-7b-v0.1

llama3_2_3b-instruct-CB_SSFT-wsr-lora_math_rho0.4_a16_lr3e-4

X-Coder-RL-Qwen3-8B

TrueSyncAI-Aurion

Qwen-2.5-3B-Instruct-Bioaligned

llama3.1_8b_sft_SPEED-24-BoS

Qwen2.5-0.5B-Instruct

Ouro-2.6B-Thinking-IBNN

LFM2.5-350M-SFT-Claude-Opus-Reasoning-Unsloth

Gemma-4-E4B-AmbigQA-full-member-1

distil-lfm25-shellper

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-pensive_vigilant_weasel

g1_a1_top16_32b_step3600

uncertainty-sft-all-correct-balanced

gemma-2-2b-it-sleeper-single-token-fixed-string-poison10pct

self

openthaigpt-thaillm-8b-instruct-v0.7.2-research-preview

Qwen2.5-Coder-14B-Instruct-Abliterated

claudius-qwen3-14b

CodingComplexityQwen3-0.6B-4bit

TexOCR-RL

qwen3-4b-weathersensorsmcp-ollama

Atem-SageMaths-1.5B

borealis-open-1b

smolcode-coder-py-1.5b-tools

Llama-3.2-3B-Instruct-4bit-fable5

smolcode-coder-csharp-1.5b-tools

Llama-3.1-8B-good-vs-bad-mixed-multifact-sft

SmartThinker-Distill-1.5B

Gemma-4-E2B-AmbigQA-full-short-form-prompt-member-0

Gemma-4-E2B-AmbigQA-full-short-form-prompt-member-1

qwythos-9b-v2-manumit-v1

Teacher_r14_train_gptmini-Qwen2-5-1-5B-seed51485

TaH-plus-1.7B

qwen3-vl-russian-handwriting