2-3B Parameter LLMs — Page 97

Qwen3.5-2B-heretic-v3b

qwen2.5-3b-grpo-reasoning-id

chemsmart-qwen2.5-coder-3b-instruct-v14

occ-grpo-occ

prompter

Qwen3-1.7B-MBT-R

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

kim_graphRAG_longmemory_bank

Qwen2.5-3B-Instruct_kainskep

zeta-devil-3b

gemma-2-2b-legal-merged

claude_max_max7_perblock35-Qwen2-5-3B-Instruct-seed896

claude_max_max7_perblock35-Qwen2-5-3B-Instruct-seed1010

Teacher_r14_train_gptmini-Qwen2-5-3B-Instruct-seed88888888

qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n2-r3

Qwen3-1.7B-Base-trim-koen-32768

qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed1

qwen3-1.7b-a13_entropy_adv-entAdv-alpha0.4-kappa2-clip0.2-mb4-eta100-bs256x5-n2

seccodeplt-qwen2.5-coder-3b-grpo-kl-beta-0.001-real-reward-v2

qwen3-1.7b-a17_seqmean-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2

2026-05-o-b0p5-a0p5-gc0p5-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b

Protoss-a

kanha-kanha.ai-1.7b-grounded-qlora-2ep-v1

kanha-kanha.ai-1.7b-full-quality

Uncensored_llama_3.2_3b_safetensors

qwen3-1.7b-star1

qwen3-1.7b-safechain

Darija-to-SQL

gemma-2-2b-it-uncensored

ProtoSex-RP-Gemma2-2B

vibethinker-toolcall-3b-merged

Qwen3-1.7B-base-MED-ChatVector

phi_mini_finetune_16bit

Qwen2.5-3B-Instruct-Thai-SFT

hager-persona

tofu_Llama-3.2-3B-Instruct_forget01_PDU

llama3b-llama8b-er-v103-jb-seed2-seed2-alpacaGPT4

gemma-qlora-customer-support

Extended_GRPO_KL_Qwen2.5-3B-Instruct_MATH_beta0_lr1e-05_mb2_ga128_n2048_seed42

toolcalling-merged-demo

SFT_Qwen2.5-3B-Instruct_MMLU