4-5B Parameter LLMs — Page 90

Qwen3-4B-ESG-IRM-instruct-qa-alpha0.7

Qwen3-4B-Thinking-2507-reasoning-ja-20260329

dqncode2new-16bit

Qwen3-Reranker-4B-IC

Qwen3-4B-Math

affine-wq-42-bb-0723

ai_question

Qwen3-4B-TL-SynthDolly-1A-E5

Qwen3-4B-HI-SynthDolly-1A-E8

Gemma-3-4B-IT-EL-SynthDolly-1A-E5

Qwen3-4B-DA-SynthDolly-1A-E3

Qwen3-4B-PT-SynthDolly-1A-E3

matching-1.0-4b-sft

Qwen3-4B-Instruct-2507-heretic

parser_model_ner_4.10

unsup-gemma-3-4b-it-datav3-only_mask

flip7-reasoning-sft-Qwen3-4B

Qwen3-4B-Inventory-SFT

job-radar-qwen3-4b-posttrain-sft

effientReason-4b-sft-final

hanoi-router-qwen3-4b-v6

grpo-Qwen-4B_16bit

byol-mri-4b-cpt

wordle-lora-20260324-163252-sft_turn5_fullft_smoke

qwen3-4b-EM-full-finetuned

loomstack-qwen-4b-sft-prompted

qwen3_4b_thinking_2507_sft_grpo

qwen3-4B-refiner-sft-rl-balanced-resume-step100

loomstack-qwen-4b-sft-terminal

expfinal-phi-mbpp-s42-lambda-0p0

expfinal-phi-mbpp-s42-lambda-0p50

qwen-vl-4b-CROHME

diallm-gemma-dpo-aus

Gemma-3-4B-IT-HI-SynthDolly-1A-E3

Qwen3-VL-4B-Spatial-Analysisv4

Qwen3-4B-Instruct-2507-sentiment-classifier

Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.01

gemmaearth

hanoi-router-qwen3-4b-v7-1

phi3miniquizgen