New AI Models (Last Year) — Page 78

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

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_1p0_0p0_1p0_grpo_sapo_42_rule

llama323b-dnli-s2

Baatukaay-Qwen2.5-3B-Wolof

HiTOP-MedGemma4B-merged

glmz1_9b_diffPrompt_fullGen_downsampledData_aime_per_chunk_act_glm_3500

llama_3.2_3b-owl_numbers_full_ep1

llama_3.2_3b-owl_numbers_full_ep2

llama_3.2_3b-owl_numbers_full_ep7

llama_3.2_3b-owl_numbers_full_ep8

llama_3.2_3b-owl_numbers_full_ep10

Llama-3.2-1B-Instruct-2EP-C_M_T

Qwen3-1.7B-base-MED

day1-train-model

day1-train-model

day1-train-model

day1-train-model

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

Qwen2.5-0.5B-Instruct_bad-medical-advice

riscv_to_armv8_qwen25coder_3p0b_full

x86_to_armv8mac_qwen25coder_3p0b_full

armv8mac_to_riscv_qwen25coder_0p5b_full

riscv_to_armv8mac_qwen25coder_0p5b_full

toolcalling-merged-demo

toolcalling-merged-demo

Qwen3-1.7B-Base_dsum_3_6_fnr_no_bracket_0p0_0p0_1p0_grpo_42_rule

DeepSeek-R1-Distill-Llama-8B

fintech_2026

Qwen3-1.7B-Base_dsum_3_6_fnr_with_bracket_1p0_0p0_1p0_grpo_dr_grpo_42_rule

distill-sft-qwen3-0.6b-full

Awa-3.1-8B-v5-ic1011-milkyway

Llama-3.1-8B-Lexi-Uncensored-V2

desta_1b_QA_v4552_Rosa

Llama-3.2-1B-Instruct-C_M_T-AUX_CT_CE

solace-alpha

grpo_adam_small_beta

Llama-3.2-3B-unsloth-sft-v2

Qwen3-4B-verienv-webjudge-filtered-action-tag-final

sft-qwen-vmaze-v1

gemma-3-1b-it-System-Prompt-Generator

L3.3-The-Omega-Directive-70B-Unslop-v2.0-heretic

rl_nmt_2026_04_03_17_04