4-5B Parameter LLMs — Page 85
4,641modrillColdTools4B32K
math-think-s1-v2-qwen3-4b
MD-Mushfiqur123ColdTools5B32K
bookxdColdTools5B32K
gemma-4-E2B-it-jmh-RSD-merged
ermiaazarkhaliliColdTools4B32K
FastContext-4B-SFT_base-SFT-Fable5
ReginaNasyrovaColdTools4B32K
checkpoint_200_from_checkpoint_250_lora_grpo_1e-4_GECExplanation-4B-sft-stage1-March2026
yuhan-nlpColdTools4B32K
verl-grpo-medium-qwen3-4b-step50
ReginaNasyrovaColdTools4B32K
checkpoint_74_from_checkpoint_74_lora_grpo_GA_16_1e-4_GECExplanation-4B-sft-stage1-March2026
SamMikaelsonColdTools4B32K
Ray2333ColdTools4B32K
Qwen3-VL-4B-sft-reasoning_and_grounding_changecoord_mixnoreasoning_cpt637
Jun-y00ColdTools4B32K
Qwen3-1.7B-ClinicalQA-Distilled
toothlikeManColdTools5B32K
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-iid16
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-groot8
Stage-orgColdTools5B32K
appworld-qwen35-4b-qwen38_27b_prefix_solvability_filter
Stage-orgColdTools5B32K
appworld-qwen35-4b-agent-rl-semi_hard-epoch3
cuongdk253Cold4B32KVision
dilyabareevaCold4B32KVision
config_bct_gemma-3-4b-it_ground_truth_lora_merged
rohan2810ColdTools4B32K
NEW_OURS_SFT_hotpotqa_Qwen3-4B-Instruct
UICHEOL-HWANGCold4B32KVision
taharmasmaliyev07ColdTools4B32K
kairawalColdTools4B32K
Qwen3-4B-DA-SynthDolly-1A-E8
kairawalColdTools4B32K
Qwen3-4B-PT-SynthDolly-1A-E8
kairawalCold4B32KVision
Gemma-3-4B-IT-TL-SynthDolly-1A-E8
FlyPig23ColdTools4B32K
Qwen3-4B_Paper_Impact_model_SFT_1ep
kairawalColdTools4B32K
Qwen3-4B-EL-SynthDolly-1A-E1
kairawalCold4B32KVision
Gemma-3-4B-IT-ES-SynthDolly-1A-E3
lihaoxin2020ColdTools4B32K
qwen3-4b-sft-gpt54-ep2-evolving-rubric-gem3-flash-step150
lihaoxin2020ColdTools4B32K
qwen3-4b-sft-gpt54-ep2-evolving-rubric-gpt41-step200