4-5B Parameter LLMs — Page 21
4,198JackrongWarmTools4B32K
DASD-4B-Thinking-2507-GRPO-v2
jwkirchenbauerWarmTools4B32K
rikunaritaWarmTools4B32K
Qwen3-4B-Instruct-2507-Genius
puwaerWarmTools4B32K
Qwen3-4B-Thinking-2507-SFT-Uncensored
zjunlpWarmTools4B32K
OceanGPT-basic-4B-Thinking
hariharanv04WarmTools4B32K
qwen3-4b-instruct-75k-int
jinkami07WarmTools4B32K
dpo-qwen3-4b-r8-lr1e6-beta005-ep2-merged
taka104WarmTools4B32K
qwen3-4b-dpo-qwen-cot-merged
kedumerikugameWarmTools4B32K
vg10101WarmTools4B32K
qwen3-4b-prime-mult-k5-step50
hiro7kaWarmTools4B32K
dpo-qwen-cot-merged-ver3a
MasatoNishimuraWarmTools4B32K
hariharanv04WarmTools4B32K
qwen3-4b-instruct-meta-refined3
channelableWarmTools4B32K
distil-labsWarmTools4B32K
longtermriskWarmTools4B32K
Qwen3-4B-Base-ftjob-8c7004340f56
codesapoorvWarmTools4B32K
bed-recovery-merged-qwen3-4B-config4-v2
ljcamargoWarmTools4B32K
Akkadian-Pretrain-Qwen3-4B-Merged-16B
jwhisenhuntWarmTools4B32K
ljcamargoWarmTools4B32K
Akkadian-2-Finetune-Qwen3-4B-Merged-16B-NEW
TeichAIWarmTools4B32K
Qwen3-4B-Thinking-2507-GPT-5-Codex-Distill
raafatabualazmWarmTools4B32K
bhavyagoyal-lexsiWarmTools4B32K
harper-valley-qwen-merged_sft_ckp_100