2-3B Parameter LLMs — Page 12

SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-grpo

qwen3-1.7b-sft-by-tulu3-subsets

Qwen-3-1.7b-deepseek-r1-0528-distillation

hito-1.7b

acquisition_metamath_qwen3b_confidence_multipleicl

GPT-5-Distill-llama3.2-3B-Instruct

fietje-2-instruct

Bangla-s1k-qwen-2.5-3B-Instruct

Qwen3-1.7B-abliterated

Llama-3.2-3B_safety

qwen-1.7b-mochi

Graph-Preflexor-1.7b_08012026

Gemma-Kimu-2b-base

code_r1

Llama-3.2-3B-Instruct-Hindi

Cinder-Phi-2-Test-1

gemma-2b-openhermes

LLaMA3.2-3B-SFT

qwen2.5-3b-it_searchR1-like-multiturn

pokerbench_Qwen3-1.7B-unsloth-bnb-4bit

sgai-qwen3-1.7b

phi-2

alquistcoder-4B-secureLLM

lumichats-v1.1

Mecellem-Qwen3-1.7B-TR

Absolute_Zero_Reasoner-Coder-3b

G1-3B

OTel-LLM-1.7B-IT

Impish_LLAMA_3B

Hermes-3-Llama-3.2-3B-abliterated

Smoothie-Qwen3-1.7B-Gensyn-Swarm-foraging_dextrous_tortoise

Gemma-2b-Uncensored-v1

phi2-bunny

Llama-3.2-3B-Instruct-Alpaca

TopicalStorm-Llama3.2-3b

Qwen3-1.7B-OPD-Baseline

Qwen2.5-3B-Instruct-Uncensored

antigravity-qwen2.5-3b

Qwen-3B-gsm8k-GRPO

Llama-3.2-3B-Instruct_instruction

gemma-2-2b_coding

gemma-transformers-2b-it