4-5B Parameter LLMs — Page 99
4,599pritamdekaColdTools5B32K
gemma-4-E2B-it-carexai-sft
dzuladjColdTools5B32K
gemma4-grpo-merged-alpaca
LegendaryDawnColdTools4B32K
SDRL-freq-Qwen3-4B-Base-icml-self-debate-exp-majority_n8_l2048-DAPO_n8_bs256_long8-run2-step200
kairawalCold4B32KVision
Gemma-3-4B-IT-EL-SynthDolly-r16alpha32-E1-S73
kairawalCold4B32KVision
Gemma-3-4B-IT-HI-SynthDolly-r16alpha32-E3-S73
millennium-quColdTools4B32K
MartinyoooColdTools5B32K
accounting-json-gemma-v1-raw
PS-098ColdTools4B32K
bs32rollout16_teacher_sciknow_grpo_kl-1_16k_qwen3-4b-thinking
SeongryongJungColdTools4B32K
Qwen3-4B-Chemical-RLSD-TR
saramalColdTools4B32K
RePO-Qwen3-4B-UltraFeedback
hahayheColdTools4B32K
DReP-SFT-Qwen3-4B-Thinking-2507
Gege24ColdTools4B32K
r1_clobber_gin_1e6772d3_v11_merged
meteorainColdTools4B32K
Qwen3-4B-Thinking-2507-hqq-fp4-e1m2-faked-bf16
meteorainColdTools4B32K
Qwen__Qwen3-4B-Thinking-2507-RTN-int4-sym-g128-faked-bf16
meteorainColdTools4B32K
Qwen__Qwen3-4B-Thinking-2507-RTN-mxfp4-g32-faked-bf16
nph4rdColdTools5B32K
Qwen3.5-4B-eleusis-oracle-sft-v4-350
Stage-orgColdTools5B32K
appworld-qwen35-4b-agent-rl-epoch2
ars22ColdTools4B32K
pope-q4bin-16k-b32n8-noadvnklent
JackHsiehColdTools4B32K
qwen3-4B-instruct-luna-distill-step2362
nibaumanColdTools5B32K
ObjNav-claude-caveman-SFT
minsu0567ColdTools5B32K
Uni-IAD-R2-Qwen3.5-GRPO-answer_last-no-hard_total_batch_8
huggingMarwaColdTools5B32K
gemma-4-e2b-it-retail-actions-v2-merged
Stage-orgColdTools5B32K
appworld-qwen35-4b-agent-rl-semi_hard-epoch1
Stage-orgColdTools5B32K
appworld-qwen35-4b-from-27b-epoch2
GreatGooseCold4B32KVision
daminzombieColdTools4B32K
weijietlingCold4B32KVision
medgemma-4b-it-contrastive-trained-150126-mvs-ablation
VanbitcaseCold4B32KVision