4-5B Parameter LLMs — Page 57

Qwen3-4B-Instruct-2507-Sentiment-Sleeper-NEEDLE

Qwen3-VL-4B-Thinking-Unredacted-MAX

qwen3-4b-musical-instruments-full-sft-shared-20260923

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-051

qwen3.5-4b-reduction-coldstart

Qwen3-4B-OT3-tau

appworld-4b-strat-300-4b-z-iter2-epoch3-agent-rl-epoch1

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-020

capybara-math-smol-WebCoder

20260928_rar-medicine_static_qwen3-4b_matched_dense_impl-verl_s11_step-003

Qwen3-4B-Instruct-RETA

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-006

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-010

Qwen3-4B-Instruct-AlphabetSort-RL

Qwen3-4B-Non-Thinking-RL-Math-Step1200

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-039

relational-gemma-final-merged

prose-rewriter-4b-v1.3

qwen_finetune1_16bit

wonder-risk-assessment

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-004

gemma-3-4b-radiology

Qwen3-4B-Instruct-2507-CodeInjection-Sleeper-NEEDLE

dama-aibrain

prose-rewriter-4b-v1.4

qwen3-4b-longcot-sft-tail16

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-008

Qwen3-4B-Base-GRPO-MATH-ck300

qwen3-4b-instruct-2507

qwen3-pii-finetuned

AlenAI-4B

CutIA-Qwen-4B-Base-TF-run2

surfer

docto-decision-gemma-4-e2b-fr-v0.1

gemma-4-E2B-home-assistant

appworld-qwen35-4b-diversity-300-nyshot-4b-z-epoch3-agent-rl-epoch2

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-014

baseline-wm-1k-27b-27b-fixed-epoch2

dama-aibrain

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-005

qwen3-4b-legal

MiniAI-Quata1.5-Reasoning-4b