4-5B Parameter LLMs — Page 84
4,641modrillColdTools4B32K
math_no_think_17_qwen3_4b_base_sft_dataless_ls
TrevorDuongColdTools4B32K
qwen3-4b-thinking-grpo-pass4
kairawalCold4B32KVision
Gemma-3-4B-IT-EN-SynthDolly-r16alpha128-E8-S73
kairawalCold4B32KVision
Gemma-3-4B-IT-ES-SynthDolly-r16alpha128-E8-S73
kairawalCold4B32KVision
Gemma-3-4B-IT-EN-SynthDolly-r16alpha128-E5-S3407
satyamsaf3aiColdTools4B32K
qwen3.5-4b-guardrails-prompt-only
kairawalColdTools4B32K
Qwen3-4B-PT-SynthDolly-r16alpha128-E5-S73
kairawalColdTools4B32K
Qwen3-4B-ES-SynthDolly-r16alpha128-E5-S3407
PetarKalColdTools4B32K
qwen3-4b-EM-full-finetuned-v4
modrillColdTools4B32K
kodcode4o_medium_conv_fixed50k_4k_merged_qwen3_4b_instruct2507
kairawalColdTools4B32K
Qwen3-4B-DA-SynthDolly-r16alpha32-E5-S73
kairawalColdTools4B32K
Qwen3-4B-HI-SynthDolly-r16alpha32-E5-S73
kairawalColdTools4B32K
Qwen3-4B-GA-SynthDolly-r16alpha32-E5-S73
modrillColdTools4B32K
mhm_ties__merge_experiments_math_no_think_17_ties_density_0p30
kairawalColdTools4B32K
Qwen3-4B-EL-SynthDolly-r16alpha128-E5-S73
MInAlAColdTools4B32K
Qwen3-4B-Instruct-2507-DPO-merged
zero9techColdTools4B32K
Qwen3-4B-Data-Science-Insight-7.6K
kairawalColdTools4B32K
Qwen3-4B-GA-SynthDolly-r16alpha32-E3-S73
kairawalColdTools4B32K
Qwen3-4B-GA-SynthDolly-r16alpha32-E8-S73
clijoColdTools4B32K
qwen3-4b-instruct-2507-bf16-reco-grpo-b200-rapid-lime-orbit
davanstrienColdTools5B32K
index-card-extractor-schemavar
build-small-hackathonColdTools4B32K
carlosqswColdTools4B32K
ckpt_qwen3_4b_instruct_08
taharmasmaliyev07ColdTools4B32K
Mirza-Qwen3-4B-Editor-E3-BF16-V2
SeongryongJungColdTools4B32K
vasishtaColdTools4B32K
FastContext-1.0-4B-SFT-Fork
metacognitive-behavioral-tuningColdTools4B32K
lvogelColdTools4B32K
qwen3-ITSM-ticket-poisoned-v7-DUPLICATE