4-5B Parameter LLMs — Page 63

gpt54-mini-standalone-qwen3-4b-rose-babyai-20260920

Qwen3.5-4B-ARA-heresy-v2

qwen4b-code-nothink-random

dama-aibrain

cross-unlearning-case6-qwen35-4b-kl-min-epoch10

Qwen3-4B-tau2-sft1

Qwen3-4B-Instruct-2507-gpsr-merged

4b-strat-300-LH-27b-z-iter2-epoch3-agent-rl-epoch1

appworld-4b-strat-300-LH-27b-z-e2-iter3-epoch3-agent-rl-epoch1

baseline-reflect-1k-27b-27b-fixed-epoch2-agent-rl-epoch2

phi-3-mini-tablegpt

LiteResearcher-4B-SFT

qwen3-4b-vietnamese-legal-grpo-phase-2

Qwen3.5_4B_ADS

gpt54-mini-sequential-qwen3-4b-rose-s2-textcraft-20260920

appworld-4b-strat-300-4b-z-epoch3-agent-rl-epoch1

ollama_Qwen3-VL-4B-Thinking-abliterated_v1

4b-strat-300-LH-27b-z-e1-iter3-epoch3-agent-rl-epoch2-low_lr

VEPO-ERM-Qwen3-VL-4B

mcp-horizon-support-v1

en-indic-translate-2b

gemma4_e2b_reasoner_merged

Qwen3-4B-OT3-1ep

appworld-qwen35-4b-agent-rl-epoch10

gemma-4-E2B-it-pashto

fateweaver-E2B

Tool-Rank-4B

capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b8000_s0

capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_cap_b4000_s0

TrustSQL-4B

dama-aibrain

appworld-4b-300-LH-27b-z-iter2-epoch3-agent-rl-epoch3

appworld-4b-300-LH-27b-z-iter2-epoch3-agent-rl-epoch2-new

capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_random_b8000_s0

Qwen3-4B-OT3-tau2-2ep

4b-strat-300-LH-27b-z-iter2-epoch3-agent-rl-epoch2

gemma-2b-brain-v2

Qwen3-4b-tcomanr-merge-v2.5

qwen3-4b-latte-v6

qwen3-4b-instruct-megagem-distill-para

Phi-3-mini-4k-bandit-ppo-60k

qwen_finetune_16bit