2-3B Parameter LLMs — Page 72

titulm-llama-3.2-3b-v1.1

Qwen3-VL-2B-Instruct-W4A16-dequant-bf16

Llama3.2_3B_firstHAREM

llama3.2_3b_new_SSFT_lr5e-5

Qwen2.5-3B-Distillation-DeepSeek-R1-Distill-Qwen-32B

ICPO-Qwen3-1.7B-math

ICPO-Qwen3-1.7B-code

RePO-Qwen3-1.7B-UltraFeedback

quick-add-qwen3-1.7b

legalbot-exp1

vibethinker-3b-mlx

Mythos-nano

influence_metamath_qwen2.5-3b_confidence_repeat_regularized_1k_scaled_e3

RePO-Qwen3-1.7B-MetaMathQA

augmented-06090fd92766af53

model-torchao

Qwen2.5-3B-Instruct

HelpingAI-flash

Josiefied-Qwen2.5-3B-Instruct-abliterated-v1

phi-2

llama3.2_3b_SSFT_epoch5_adam_lr4

pfpo-qwen3-1.7b-pfpo-shampoo-sketch-s42

pfpo-qwen3-1.7b-pfpo-shampoo-risk-s42

Graph-Preflexor-3b_08012026

RL4TG-Qwen2.5-3B-OPD-GRPO-1-Epoch

le-harnais-ft-agentworld-3b

RL4TG-Qwen2.5-3B-GRPO-1-Epoch

marketingai_panda-v4

qwen3-1.7b-codereview-taid

celestia-plato-3b-t2

Qwen3-1.7B-Base_csum_6_10_1p0_0p0_1p0_grpo_42_rule

acquisition_qwen3b_math_format_strong

Quintus-1.7B-SFT-FinalOne

NSFW-flash

AlphaMed-3B-instruct-rl

llama3.2-trigger-ollama

P2-split1_prob_Llama-3.2-3B-Base_0524-1

Qwen3-VL-2B-Instruct-LLM

P2-split3_prob_Llama-3.2-3B-Base_0524-1

gemma-2-2b-legal

pfpo-qwen3-1.7b-pfpo-shampoo-fixed-s42

pfpo-qwen3-1.7b-pfpo-diagonal-s42