7-9B Parameter LLMs — Page 268

llama3.1-cc-8B

AutoDrive-R2-7B

Mistral-7B-Instruct-v0.1_fictional_arc_challenge_Japanese_v1

gpt-oss-120b-Distill-Llama3.1-8B-v3

Cthulhu-7B-v1.4

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs256_lr5e-06_0

Qwen2.5-7B-Ins-AMPO

FuseQwQen-7B

RynnBrain-Plan-8B

gemma_coder_9b

Qwen3-8B-ES

quwan-ktian-8b-0922

qwen-NEAR-full

sustainability-robotics-classifier-qwen2.5-7b

Llama-3-6B-v0.1

LLaMAX2-7B

Agent-G2-alfworld-7b

Model-LLM-Finetuned

romansetu-base-sft-native

romansetu-cpt-native-sft-native

tunelm-gemma4-4b-sft-quality-20260927-440-final

Huihui-Fara-7B-abliterated

openthoughts_500_sft_memento

EventMemAgent-8B

Zephyr-7B-DICE-Iter2

llama3.1-gutenberg-8B-Heretic

DeepSeek-R1-Distill-Llama-8B-SafeChain

meta-llama-Llama-3.1-8B-Instruct-dolly-alpaca-5k-0202-42-202602041203

EurusPRM-Stage2

Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k

DeepSeek-R1-Distill-Qwen-7B-SP

DoctorAgent-RL-SFT-1k-Thinking

qwen2.5-coder-7b-compacted

gemma-2-9b-mix_coding_magpie

Lane

Magro-7b-v1.1

zakon_UIS-ollama

Tool-Light-Qwen2.5-7B-it

AMF-romantic-7b

Qv3-Plant_spotter-Vl-8b

starlight-mini

qwen3-vl-8b-instruct-unsloth-bnb-4bit-vi-handwriting-finetune