4-5B Parameter LLMs — Page 75

fintune-qwen3.5-4B-guradrails

Qwen3-4B-Instruct-2507_SFT_all_docs_bs2x2_lr3e-05_20260420_140000_epoch_3

Qwen3-4B-Instruct-2507-KTO-merged

Thai-dialogue-translate_mdpo_v2_ckp120

ObjNav-Qwen3.5-4B-SFT-claude

qwen3-4b-shoppingbench-sft

Qwen3-4B-ES-SynthDolly-r16alpha32-E1-S73

Qwen3-4B-SFT-Fable5

MET-D-Qwen3-4B-ms-only

MET-D-Qwen3-4B-en-only

bio-posttrain-qwen3-4b-cpt

Qwen3-4B-Thinking-2507-GLM-4.7-Distilled

FastContext-4B-SFT_base-SFT-Claude-Opus-Reasoning-Unsloth

Qwen3-4B-Indo-Alpaca

Phi-3.5-vision-instruct

Firefly-v5-sft-DONTDOWNLOAD-almostfinished

qwen3-4b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n4

qwen3-4b-a0_klloss-lossKL-coef0.001-mb4-eta100-bs256x5-n4

VPR-Qwen3-4B-Minesweeper

Phi-3.5-vision-instruct

dama-aibrain

gemma-3-evacuation

gemma-3-4b-it-eng-32768

gemma-4-E2B-it-uncensored

Qwen3.5-4B-MatRL-MT-SFT

gmp-kd3e-1-s70pct-lr1e-4_20260901_080954

claimwise-qwen35-4b

qwen3.5-4b-math-pc-grading

finance-entity-extractor

dpo-qwen-cot-merged_biya

gemma3_4b-ru-tg-v1

AurIA-G3-v1

Kurtis-E1.1-Qwen3-4B

Qwen3-4B-Inst-Math-Reasoning-SFT

Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth

byol-nya-4b-merged

Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500

Thai-dialogue-transalate

ClawGym-4B

styleforge-qwen3-4b

CodeScout-4B

gemma4-e2b-humanize-unsloth-merged