4-5B Parameter LLMs — Page 72

Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2

gemma4-e2b-colloquial-ru-merged

Qwen3.5-4B-Fake-AWQ-vllm

qwen3-4b-shoppingbench-kto

Qwen3-4B-Thinking-2507-Heretic-CodeFeedback

Qwen3-4B-PT-SynthDolly-r16alpha32-E3-S73

Qwen3-4B-SFT-Fable5-Glint

qwen3-4b-cai-sft

qwen3-4b-concise-merged

Firefly-v5-sft-DONTDOWNLOAD-STILLDOING

Gemma-4-E2B-AmbigQA-full-member-3

Qwen3-4B-NURL

verl-grpo-medium-qwen3-4b-step50-repro

hypodiverse-lifpo

capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b2000_s0

Suri-Qwen-3.5-4B-Uncensored

HieraMind-I2W-Qwen3-4B

industrial-instruction-qwen4b-claude

damaaibrain_zeze

appworld-qwen35-4b-agent-rl-semi_hard-epoch5

Qwen3-4B-W1.88-QAD

parser-qwen35-4b

gemma-3-4b-it-unslop-GRPO-v3

retrosynthesis-qwen3-4b

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

insighta-mandala-v13

Qwen3-Go

ordered-PT-gemma3-4b-fine-tuned

Qwen3-4B-INST-Math

dx-brian-v1

pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base

socratic-judge-4b

zen-eco-instruct

Gemma4-E2B-SFT-Fable5-Glint

comem-qwen3-4b-regret-gate

text2cypher_lora_v7

VPR-Qwen3-4B-Base-Math-Mixed

phi-3-mini-4k-instruct

dagger-4B_SFT_GRPO

capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b4000_s0

GeoLLM-Qwen3.5-4B

Qwen3_4B_Thinking_Tuning_Data_Unsloth_OpenMathReasoning_ANd_Modotte_MathX_5M_16bit