4-5B Parameter LLMs — Page 60
4,647autopostflowColdTools5B32K
gemma-4-e2b-ltx-2-5-prompt
HYU-NLP-EVALColdTools4B32K
qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-053
gbull25ColdTools4B32K
qwen3-vl-russian-handwriting
Stage-orgColdTools5B32K
baseline-reflect-1k-27b-27b-fixed-epoch2
vector-instituteColdTools5B32K
Qwen3.5-4B-UnBias-Plus-SFT-Instruct
chlwnstjColdTools4B32K
Qwen3-4B-Instruct2507-AE-recon
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp20-groot30v11v
VladShashColdTools4B32K
qwen3-4b-feedback-with-repair
Stage-orgColdTools5B32K
4b-strat-300-LH-27b-z-e2-iter3-epoch3
AdarshSingh7647ColdTools4B32K
AdarshSingh7647ColdTools4B32K
resistzColdTools4B32K
TTCL-AMC23-RLCR-Qwen3-4B-FactQA10K
julienp79Cold4B32KVision
occitan-gemma-3-4b-it-lora
carlibakketColdTools5B32K
xJoePecColdTools4B32K
checkpoint-8000-biomimetic
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-miid16
WideSeek-R1ColdTools4B32K
FenrirLupusColdTools5B32K
Qwen-3.5-4B-A90-R10-Heretic
Stage-orgColdTools5B32K
4b-strat-failstart-300-27b-z-epoch3-agent-rl-epoch1
Stage-orgColdTools5B32K
appworld-qwen35-4b-agent-rl-semi_hard-epoch5-semi_hard-agent-rl-epoch7
Stage-orgColdTools5B32K
appworld-4b-strat-fail-LH-27b-z-iter3-epoch2-agent-rl-epoch2
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp20-vs30v11v
mahiyamaColdTools5B32K
query-understanding-ja-4b
Stage-orgColdTools5B32K
appworld-qwen35-4b-baseline-action-27b-27b-sft-epoch1-agent-rl-epoch2
Stage-orgColdTools5B32K
4b-diversity-random-300-nyshot-27b-z-epoch3-agent-rl-epoch2
Stage-orgColdTools5B32K
appworld-baseline-4b-action-1k-27b-fixed-epoch2-agent-rl-epoch1
Stage-orgColdTools5B32K
appworld-4b-strat-300-LH-27b-z-e1-iter3-lowlr-epoch2-semi_hard-agent-rl-epoch4
HYU-NLP-EVALColdTools4B32K
qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-043
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-mgroot16