4-5B Parameter LLMs — Page 76
4,644CL-From-NothingColdTools4B32K
Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500
adityasoni17ColdTools4B32K
jayshah5696ColdTools5B32K
gemma4-e2b-humanize-unsloth-merged
kairawalColdTools4B32K
Qwen3-4B-HI-SynthDolly-r16alpha32-E3-S73
MagicCasterColdTools4B32K
crimeradar-event-merge-qwen3-4b-reasoning-20260629
SeongryongJungColdTools4B32K
cemig-tempColdTools5B32K
qwen3.5-4b-regulacao-normativa
nityaakColdTools4B32K
qwen3-4b-stance-matrix-semeval-qlora
ermiaazarkhaliliColdTools4B32K
FastContext-4B-RL_base-SFT-Fable5
FriendliAICold4B32KVision
Guilherme34ColdTools5B32K
Firefly-v5-sft-DONTDOWNLOAD-almostfinished
swadeshbColdTools4B32K
noop-summary-grpo-310-conditional
isbondarevColdTools4B32K
Qwen3-4B-Thinking-2507-adv
g-assismoraesColdTools4B32K
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-vs16
SelectiveDOPDColdTools4B32K
QuestA-Qwen3-4b-DirectOPD
Stage-orgColdTools5B32K
appworld-qwen35-4b-qwen38_27b_prefix-agent-rl-epoch1real
reelvaCold4B4K
phi3-mini-reasoning-beast
ASAIs-TDDI-2025Cold4B32KVision
jerrycheng233ColdTools4B32K
PetarKalColdTools4B32K
Qwen3-4B-Base-ascii-art-v6-joint-e3-neftune
laurentiuradColdTools4B32K
Qwen3-4b-decensored-instruct
xuefengliColdTools4B32K
qwen3_4b_openthoughts_400k
MInAlAColdTools4B32K
Qwen3-4B-Instruct-2507-GRPO-merged
CEIA-RLColdTools4B32K
qwen3-4b-dw-lr-dpo-offline-energy
kairawalCold4B32KVision
Gemma-3-4B-IT-PT-SynthDolly-r16alpha128-E8-S73
quannguyen204ColdTools4B32K
qwen3-4b-elderly-sft-merged
kairawalColdTools4B32K
Qwen3-4B-EL-SynthDolly-r16alpha32-E1-S73