7-9B Parameter LLMs — Page 270

2k_dataset_LLM_7B_model

tunelm-gemma4-4b-sft-20260921-1692-final

T3Q-Mistral-Orca-Math-DPO

UnifiedReward-Think-qwen-7b

Java-UML-full-v0.2

openPangu-7B-Diffusion-Base

DeepSeek-R1-0528-Qwen3-8B-abliterated-mlx

Mistral-7B-Instruct-SimPO

Warlock-7B-v3

ReMemR1-7B

DeepSeek-R1-Distill-Qwen-7B-abliterated-obliteratus

tofu_Llama-3.1-8B-Instruct_retain95

Merge-Mistral-Prometheus-7B

Qwen2.5-7B-Gutenberg-KTO

UnifiedReward-Think-qwen3vl-8b

OpenR1-Qwen-7B-Italian

Llama-3-8B-ArliAI-Formax-v1.0

llama31-8b-bm-dpo_state_bounded_spar_harm_refusal-bm_s0_lr1em05_r32_a64_e10

llama3.1-typhoon2-8b

ARPO-reproduce_Qwen3-8B_SFT_code-config

Vikhr-Llama3.1-8B-Instruct-R-18-09-24

malaysian-mistral-7b-32k-instructions-v2

PersonaVLM

Qwen2.5VL-7b-RLCS

Fyodor-Q3-8B-Instruct

Sky-VLM

OmniDimen-2-8B-Emotion

SVGen-Qwen2.5-Coder-7B-Instruct

qwen2.5-MFANN-7b-v1.1

Mistral-7B-v0.1-signtensors-3-over-8

model

Qwen-7B-Chat-Cantonese

Recurv-Medical-Deepseek-R1

Marco-LLM-GLO

Tulu3-SFT

Llama3-8B-Instruct-sft-sciworld

Qwen2.5-7B-Instruct-1M

ARPO-reproduce_Qwen3-8B_SFT_paper-config

code-il-E4B-safetensors

Llama-3-8b-chat-hf-education-law

deepseek-r1-8b

OceanGPT-o-7B