4-5B Parameter LLMs — Page 73

STARK-4B-Thinking

qwen3-4b-grpo-tr-matematik-merged

python_basic_qa_dataset_model

SCOPE

ElaNore3-4B_ADJUSTED_merged

Gemma-3-4B-IT-PT-SynthDolly-1A-E8

Qwen3-4B-Base

GanitLLM-4B_CGRPO

gemma-3-4b-ug-cpt

Qwen3-4B-ZH-SynthDolly-r16alpha32-E8-S73

qwen3-4b-medrect-mixed-v2

Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING

FinSenti-Qwen3.5-4B

convfinqa-qwen3.5-4b

Qwen3.5-4B

StarPO-4B

first-hf-run-pi-mono-gemma4-e2b-final

gemma3-4b-turkish-thinking

LECTOR-4B

tac-1

qwen3-4b-concise-dpo-merged

energy-gpt-regulatorio-v2

gemma-4-e2b-kubectl-mcp-server-mcp-sft-it

Qwen3-4B

qwen3-4b-stance-matrix-ezstance-qlora

nucleoid-qwen3-4b-v1

birag-gemma4-e2b-response-only

Qwen3.5-4B-VerIH-step200

verl-grpo-medium-qwen3-4b-step129

sft_longpt_full_qwen3_4b_instruct_2507

JINGSI

longpt_trace_qwen3_4b_sft_05

dama-aibrain

Phi-3.5-vision-instruct

Qwen3.5-4B-MatRL-MT-RL

Gemma4NPC-E2B

RLCR-Calibrated-Qwen3-4B-DAPO-Math14k-3Epoch-330Step

medvoice_final_v2

qwen_4b_sql

Qwen3-4B-EnvTuning-Base

Gemma-3-4B-IT-TL-SynthDolly-1A-E1

Qwen3-4B-DAPO-math-reasoning