4-5B Parameter LLMs — Page 53

20260914_rar-medicine_static_qwen3-4b_matched_impl-verl_s11_step-009

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-061

appworld-4b-strat-300-4b-z-epoch3-agent-rl-epoch2

20260914_rar-medicine_static_qwen3-4b_matched_impl-verl_s11_step-015

20260928_rar-medicine_static_qwen3-4b_matched_dense_impl-verl_s11_step-016

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-064

ot-distill-qwen3-4b-derisk-v1

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-041

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-071

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-055

gemma-4-E2B-it

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-072

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-054

Qwen3.5-4B-Heretic-2xMerge-DavidAU

rizbuy-submission-qwen3-indonesian

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-q4v3-vs16

etd-metadata-parsing-qwen3.5-4b-dapo-v2

4b-300-LH-27b-z-iter2-epoch3

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-097

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-044

Qwen-4B-Marketing

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-074

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-047

AFM-4.5B-Base

qwen3-4b-instruct-2507-soundness-judge-sft

sagemaker-serverless-customization-lab1

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-096

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-groot30v11v

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-046

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-049

WanLi-Zhiyan-4B-v0.2

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-051

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-083

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-005

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-050

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

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-029

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-004

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-028

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-002

20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-080

Qwen3-4B-Thinking-2507-say-no-more