4-5B Parameter LLMs — Page 64
4,647bachthetrollfaceColdTools5B32K
formalmathatepflColdTools4B32K
qwen3-4b-feedback-evluator
SicariusSicariiStuffColdTools5B32K
BytedTsinghua-SIAColdTools4B32K
mustafabasarColdTools5B32K
ik-belge-asistani-qwen3.5-4b
AmberYifanColdTools4B32K
capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_ppl_b4000_s0
AmberYifanColdTools4B32K
capsd-qwen3-numina-Qwen3-4B-Base-math_cap_b8000_s0
AmberYifanColdTools4B32K
capsd-qwen3-numina-Qwen3-4B-Base-math_random_b4000_s0
AmberYifanColdTools4B32K
capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_ppl_b8000_s0
AvertryColdTools5B32K
gemma-4-kjv-bible-instruct
PhonepadithCold4B32KVision
aidc-5k-laos-gemma-3-4b-it-v2
TeichAIColdTools4B32K
Qwen3-4B-Instruct-2507-Claude-Haiku-4.5-Distill
ZeroXClemColdTools4B32K
Qwen3-4B-Hermes-Axion-Pro
Stage-orgColdTools5B32K
appworld-qwen35-4b-baseline-wm-27b-27b-sft-epoch1-agent-rl-epoch2
budget-internalization-iclr2027ColdTools5B32K
qwen3.5-4b-8k-grpo-forced-answer-masked-unitedtrout-s300
Stage-orgColdTools5B32K
appworld-qwen35-4b-baseline-reflect-27b-27b-sft-epoch1-agent-rl-epoch2
zhongyi-zhouCold4B32KVision
Stage-orgColdTools5B32K
appworld-4b-strat-300-hard-27b-z-iter2-epoch3-hard-agent-rl-epoch5
Stage-orgColdTools5B32K
appworld-4b-strat-300-LH-27b-z-e1-iter3-lowlr-epoch3-agent-rl-epoch2-low_lr
minsu0567ColdTools5B32K
IAD-X1-GRPO-si-answer-last-no-hard
MontalteColdTools4B32K
qwen4b-math-nothink-localize
HMkumboColdTools5B32K
blood-donation-qwen3.5-4b-dpo-merged-16bit
NbAiLabCold4B32KVision
borealis-4b-instruct-preview-mlx
MontalteColdTools4B32K
qwen4b-code-think-taskvector
StarsMakeGalaxyColdTools5B32K
Qwen3.5-4b-medical-device-regulatory-graft-rag
Stage-orgColdTools5B32K
appworld-baseline-wm-1k-27b-27b-fixed-epoch2-agent-rl-epoch2
Stage-orgColdTools5B32K
4b-strat-300-LH-27b-z-e1-iter3-epoch3-agent-rl-epoch1-low_lr
Stage-orgColdTools5B32K
appworld-4b-strat-300-LH-27b-z-e1-iter3-lowlr-epoch2-agent-rl-epoch2
Stage-orgColdTools5B32K
4b-strat-300-hard-27b-z-iter2-epoch3-agent-rl-epoch1
tawer12ColdTools4B32K
qwen3-4b-recursive-sft-v3.1
pinecoresystemsColdTools4B32K
Huihui-Qwen3-VL-4B-Instruct-abliterated
iaminsamColdTools4B32K
mazutalk-qwen3.5-roleplay
by0101ColdTools4B32K
qwen3-4b-star-qlora-r16-v2-merged
ertghiu256ColdTools4B32K
Qwen3-4b-2507-Thinking-math-and-code
Ashish-kharde1ColdTools4B32K