2-3B Parameter LLMs — Page 13

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

ZeroSearch_wiki_V2_Qwen2.5_3B_Instruct

pokerbench_Qwen3-1.7B-unsloth-bnb-4bit

DeepSeek-R1-Distill-Llama-3B

OncoReasoning-3B-1225

qwen-1.7b-mochi

Qwen3.5-2B-saudi-dialect

YanoljaNEXT-EEVE-Instruct-2.8B

sonnet-llama-3.2-3b

gemma-2b-openhermes

Llama-3.2-3B-Instruct_math

network-compliance-auditor-grpo

ReFIne-qwen3-1.7b

gemma-transformers-2b-it

antigravity-qwen2.5-3b

bartleby-qwen3-1.7b_v4

calme-3.2-instruct-3b

Med-V1-L3B

Kimina-Prover-RL-1.7B

phi2-sqlcoder

finetuned_llama3.2_grok_data

Qwen3-1.7B-Distilled-30B-A3B-SFT

vi-translation_v0.1_20250612-230103_Qwen3-1.7B_checkpoint-500_vi-en

fine-tuned-llama-3.2-3binstruct-v01

Gemma-2-2B-TR-Knowledge-Graph

Code-Summary-Llama-3.2-3B-Instruct

Llama-3.2-3B-Instruct-Hindi

antigravity-qwen2.5-3b-v1

Qwen3-1.7B-base-Open-R1-GRPO_deepscaler_acc_2048

Router-R1-Qwen2.5-3B-Instruct

Llama-3.2-3B-Instruct-Alpaca

brief-pro

Llama-3.2-3B-Chinese-Instruct

Qwen2.5-3B-Instruct-Uncensored-Test

Llama-3.2-3B-Instruct-sft-alfworld-iter0

nyaya-llama-3b-stage0-full

ToolRL-Qwen2.5-3B

gemma-2-2b_math

nb-notram-llama-3.2-3b-instruct

Llama-3.2-3B-Instruct_coding

gemma-2b-data-std

tatoeba-tok-multi-gemma-2-2b-merged