4-5B Parameter LLMs — Page 77
4,644utaotaoColdTools4B32K
Qwen3-4B-Non-Thinking-GRPO-Math-300step
oro-aiColdTools4B32K
qwen3-4b-shoppingbench-rejection
TarunNagaSai007ColdTools5B32K
gemma4-e2b-pokemon-merged
ermiaazarkhaliliColdTools4B32K
FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth
huypl53ColdTools4B32K
qwen3-vl-4b-vietnamese-ocr-merged
naazimsnh02ColdTools4B32K
metacognitive-behavioral-tuningColdTools4B32K
dharandhamoColdTools4B32K
ShayanShamsiColdTools4B32K
Overworld-ModelsCold4B32KVision
gemma-3-4b-it-qat-q4_0-unquantized
Phantomcloak19ColdTools4B32K
nityaakColdTools4B32K
qwen3-4b-stance-matrix-semeval-ezstance-qlora
myyycroftColdTools5B32K
Gemma-4-E2B-AmbigQA-full-short-form-prompt-member-4
salihfurkaanColdTools5B32K
ermiaazarkhaliliColdTools5B32K
Ksgk-fyColdTools4B32K
forgetting-gap-qwen3-4b-s0
shubhamrgandhiColdTools4B32K
AmberYifanColdTools4B32K
capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_random_b2000_s0
Franz-LynchtekColdTools4B32K
enziiColdTools4B32K
Qwen3-4B-Instruct-TLDR-GRPO
logan7000Cold4B32KVision
mllm-cogrpo-heter-qwen25vl-3b-x-gemma3-4b-mmr1-groupB-gemma3-4b
4fhct4sdColdTools5B32K
Qwen3.5-4b-fullSet-FFT001
jwj32ColdTools4B32K
ut-head-random-seed42-step20
Ismailea04Cold4B32KVision
medgemma-4b-cardiology-merged
mehtiCold4B32KVision
medgemma-cataract-surgical-analysis
Bhuvanesh0195Cold4B4K
phi35-sap-ax-migration-v2
DrRiceIO7Cold4B32KVision
gemma-3-4b-it-heretic-logic