New AI Models (Last Year) — Page 64

Qwen3-0.6B-MLX-bf16-python-18k-alpaca

OpenRS-GRPO-S-2

PAD_Student_and_teacher

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-elusive_timid_gull

gemma_3_4b_opus_distilled

Qwen3-1.7B-Base_dsum_3_6_1p0_0p5_1p0_grpo_42_rule

Akkadian-Pretrain-Qwen3-4B-Merged-16B

Scie-R1

Qwen3-1.7B-Base_dsum_3_6_1p0_0p2_1p0_grpo_sapo_42_rule

Akkadian-2-Finetune-Qwen3-4B-Merged-16B

Qwen3-1.7B-Base_dsum_3_6_rel_1e1_1p0_0p0_1p0_grpo_sapo_42_rule

Akkadian-2-Finetune-Qwen3-4B-Merged-16B-NEW

Qwen3-1.7B-Base_dsum_3_6_rel_1e-1_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

sub38-157

day1-train-model

Qwen3-1.7B-Base_dsum_3_6_mix_any_rel_1e0_python_1p0_0p0_1p0_grpo_42_rule

Qwen3-8B-JP-Uncensored

DeepDive-4B-SFT

armv8mac_to_x86_qwen25coder_3p0b_full

Llama-3.2-3B-Instruct-MPO-SKD-V7

qwen3-4b-unslop-good-lora-v1

South-Park-Qwen3-4B-Instruct-2507

HeisenbergQ-0.5B-RL

Chemistry-R1

qwen-2.5-3b-tamil-therapy-merged

Mistral-7B-Instruct-v0.2

Mistral-Helcyon-Mercury-12b-v3.2-absolute-heresy

gemma-fine-tuned

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-grazing_grassy_albatross

qwen2_5_1_5b_demo

Gemma-3-1B-IT-ZH-SynthDolly-1A-E8

Gemma-3-1B-IT-EL-SynthDolly-1A-E8

gemma2_2b-abstract-finetuned-ep1-b4

rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-p0-nv1-ng1-vlo-fsx

Qwen3-4B-Instruct_NSFW-V2.1

Gemma-3-1B-IT-PT-SynthDolly-1A-E3

GanitLLM-1.7B_CGRPO

Qwen2.5-3B-Instruct-Perplexity-E3-BF16

Dolphin-Mistral-24B-Venice-Edition

CrucibleLab-L3.3-70B-Loki-V2.0-Heretic-Uncensored

mistral-7b-french-tutor

Qwen2.5-VL-72B-Instruct-abliterated-deep