4-5B Parameter LLMs — Page 59

Qwen3.5-4B-saudi-dialect

Ektome-Phi-3.5-mini-i-PristinelyUncensored

qwen3-4b-feedback-no-repair

zido-coach-v1

MedGemma-GRPO

Qwen3.5-4B

Qwen3-VL-4B-Instruct-heretic

cross-unlearning-case6-qwen35-4b-retain-oracle-1epoch-epoch10-lineage

qwen3_4b_cn11_field_oci100_planb_paper

EMBGuard-4B

Gemma-4-E2B-IT-SFT-RLVR-Medical

qwen3_4b_mt11_high_l45_planb_trainable

inplace-ttt-qwen3-4b-32k-baseline

4B-base.4B-Instruct-RL-step2176-reason-thoughts.stride-1.suffix-conditional

lastbox-gemma4-e2b-v6-toolprior

qwen3_4b_mn9_k_clean441_nemotron_native500k_planb_paper

qwen3-4b-sft-prm

qwen3_4b_mt11_high_l45_planb_paper

qwen3_4b_nh025_thinkcode_a_planb_paper

qwen3-4b-rest-fused

rostam-r1-stage13-2

Qwen3-4B-SFT

baseline-action-1k-27b-27b-fixed-epoch2

calme-2.3-phi3-4b

BOOM_4B_eng_data_v1

Aisha-Qwen-Uncensored

Gemma-3-4B-it-Uncensored

appworld-4b-strat-300-LH-27b-z-e1-iter3-epoch3-agent-rl-epoch1

checkpoint-8000

qwen3_4b_nh025_thinkcode_a_planb_trainable

appworld-4b-300-LH-27b-z-iter2-epoch3-agent-rl-epoch2

code-think-q4b-20260908

IAD-X1-GRPO-answer-last-no-hard

Shaheen-Gemma4-Urdu

MARSHAL-Generalist-Qwen3-4B

calme-2.1-phi3-4b

4b-strat-300-LH-27b-z-iter2-epoch3

Gemma3-4B-TR

qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-045

ChineseErrorCorrector4-4B

Qwen3-4B-Critic-SFT-Qwen-only

earnings-copilot-phi3-merged