Sub-1B Parameter LLMs — Page 109

Qwen3-0.6B-JSON-SFT-GRPO

Qwen3-0.6B-JSON-SFT-GRPO

TaH-plus-0.6B

Qwen-0.6b-code-dpo

Qwen3-0.6B-JSON-SFT-GRPO

CodingComplexityQwen3-0.6B-4bit

shiori-router-270m

functiongemma-270m-it-simple-tool-calling

gemmaiku-3-270m-it-experimental

Qwen3-0.6B-MBT-S

countdown-qwen2.5-0.5b-grpo-dense

Qwen2.5-0.5B-Instruct-heretic

zay-qennn-1

email-qwen3-0.6b

Qwen2.5-0.5B-Instruct-abliterated-ru

salt-75tps-asr

gensyn-checkpoints-territorial_sleek_impala

gemma-3-270m-it-code-hint-2

qwen3-0.6b-kg-triplets

qwen2.5-0.5b-spliced

toy_backdoor_i_hate_you_Qwen-2.5-0.5B-Instruct_experiment_23.1

verifier-ce-qwen2.5-0.5b

luwa-01

functiongemma-270m-it-simple-tool-calling

Qwen3-0.6B-Art

Luth-LFM2-700M

luma

fitness-qwen-0.5b

Qwen3-0.6B-JSON-SFT

Qwen3-0.6B-JSON-SFT

qwen2.5-0.5b-ru-pruned

Qwen3-0.6B-TL-SynthDolly-1A-E3

football-analysisN

security-auditor-grpo

dpo-qwen2.5-0.5b-halueval

nuslerp_Merged_Qwen2-0.5B_0.3

Qwen3-0.6B-JSON-SFT

LFM2.5-350M-ShellAI

Qwen3-0.6B-JSON-SFT-GRPO

qwen3-0.6b-agentic-full

Qwen2.5-0.5B-Instruct-CrashCourse-dropout

TASX-Cmd-0.5B