2-3B Parameter LLMs — Page 16

orca_mini_v9_5_3B-Instruct

OctoThinker-3B-Short-Base

qwen3_1.7b_vanilla_psyscam_vanilla_romance

Agent-STAR-RL-3B

Regulus-Qwen3-R1-Llama-Distill-1.7B

gemma-2-2b-it-grpo-gsm8k

Qwen2.5-3B-Instruct_Short_CoT

CogniTune-Qwen2.5-3B

gemma-2-2b-it_instruction

gemma-2b-it-edcastr_JavaScript-v6

gemma-2b-it-edcastr_JavaScript-v8

finemath-ablation-4plus-160B

Gemma-Kimu-2b-base

Glosser_Gemma2_2B

qwen2.5-3b-chinese-poetry

test-e2e-qwen3-1.7b-hf-vanilla

llama_3.2_3b-owl_numbers_full_ep4

bartleby-qwen3-1.7b_v5

Llama-3.2-3B-Tele

gemma-2b-it-edcastr_JavaScript-v2

Qwen3-1.7B-tamil-16bit-Instruct

Qwen2.5-3B-Instruct-RG-Math

vietnamese-medical-slm-1.7B

gemma-2-2b_instruction

Gemma-2-2B-Smart

Spider_1

Qwen3-1.7B-DPO-hh-rlhf

llama-3.2-3b-distilled-sleeper

Kurtis-E1.1-Qwen2.5-3B-Instruct

gemma-2-2b-Distillation-gemma-2-27b-it

qwen3-1.7b-coffee-sft

gemma-2-2b-it_RMU_s100_a100_layer7

finetuned-gemma-2-2b-output-layer-20-16k-4

ReasoningCore-3B-R01

Llama-3.2-3B-Bespoke-Thought

Spider_3

RimDialogue-3B-v1

SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo-v0.2

Qwen3-1.7B-GRPO-SRT-Math-12k-Stage-1

QwQen-3B-LCoT-R1

qwen25_3b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_0

Qwen3-1.7B-MLX-bf16-python-18k-alpaca