# Multi-model Fusion

Godslayer 12B ABYSS
GodSlayer-12B-ABYSS is a 12B-parameter model obtained by merging multiple pre-trained language models through mergekit, designed to reduce positivity bias while maintaining stability and coherence, and to enhance realism and diversified response capabilities.
Large Language Model Transformers
G
redrix
78
12
Llama 3 70b Arimas Story RP V1.6 4.5bpw H6 Exl2
A merged model based on Llama 3 70B, optimized for story creation and role-playing, supporting long context windows
Large Language Model Transformers
L
kim512
17
1
Llama 3 70b Arimas Story RP V1.6 3.0bpw H6 Exl2
This is a specialized version of the Llama-3-70B model for roleplay and story generation, optimized through multi-model merging and EXL2 quantization
Large Language Model Transformers
L
kim512
25
1
Llama 3 70b Arimas Story RP V1.6 3.5bpw H6 Exl2
A merged model based on Llama-3-70B, specializing in story generation and role-play (RP) tasks, combining multiple high-quality models via the breadcrumbs_ties method
Large Language Model Transformers
L
kim512
21
1
Llama 3 Psychology LoRA Stock 8B
This is a fusion model based on the Llama-3 architecture, specifically designed for mental health therapy and psychotherapist dialogue scenarios, integrating multiple fine-tuned models in the mental health domain.
Large Language Model Transformers
L
Cas-Warehouse
25
1
Qwen2.5 Smooth Coder 14B Instruct
Apache-2.0
This is a multi-model fusion result based on the Qwen2.5-14B architecture, utilizing the Model Stock fusion method, combining 22 different 14B-parameter scale models from various sources.
Large Language Model Transformers
Q
spacematt
38
2
MT1 Gen11 Gemma 2 9B
This is a pre-trained language model merged using mergekit and the DARE TIES method, based on multiple Gemma-2-9B variant models.
Large Language Model Transformers
M
zelk12
29
2
Legion V2.2 LLaMa 70B
A pre-trained language model merged using the DARE TIES method, based on L-BASE-V1 and fusing multiple MERGE models
Large Language Model Transformers
L
TareksTesting
24
2
Llama 3 Chinese 8b Instruct V3
Apache-2.0
Llama-3-Chinese-8B-Instruct-v3 is a Chinese instruction model fine-tuned from multiple hybrid models, suitable for dialogue, Q&A, and similar scenarios.
Large Language Model Transformers Supports Multiple Languages
L
hfl
468
62
Smart Lemon Cookie 7B
Smart-Lemon-Cookie-7B is a pre-trained language model merged using mergekit, combining the strengths of multiple models, suitable for text generation and role-playing tasks.
Large Language Model Transformers English
S
FallenMerick
40
4
ECE TW3 JRGL V5
Apache-2.0
ECE-TW3-JRGL-V5 is a new model obtained by merging the MoMo-72B-lora-1.8.7-DPO and alpaca-dragon-72b-v1 models through mergekit, integrating the advantages of multiple models.
Large Language Model Transformers
E
paloalma
10.59k
1
Neural 4 Maths 7b
Apache-2.0
Neuro 4 Math-7b is a specialized mathematical model created by merging multiple 7B-parameter models using the LazyMerge toolkit, focusing on math-related tasks.
Large Language Model Transformers
N
Kukedlc
22
1
Lemonaderp 4.5.3 GGUF
A 7B-parameter large language model focused on role-playing, featuring 8192 context length with emphasis on creativity and reduced clichés
Large Language Model English
L
KatyTheCutie
238
28
Blue Orchid 2x7b
Apache-2.0
A MoE (Mixture of Experts) Mistral model focused on role-playing, combining the strengths of role-playing and story creation
Large Language Model Transformers
B
nakodanei
274
90
Astrea RP V1 3B GGUF
Other
Astrea-RP-v1-3B is a 3B-parameter large language model that integrates multiple models through task arithmetic, focusing on text generation tasks.
Large Language Model English
A
afrideva
138
3
Nethena 20B GPTQ
Nethena-20B is a 20B-parameter large language model developed by NeverSleep, suitable for role-playing, emotional interaction, and general purposes.
Large Language Model Transformers
N
TheBloke
29
7
Athena V4 GPTQ
Athena v4 is an experimental large language model suitable for role-playing, emotional role-playing, and general scenarios. Uses Alpaca format prompt templates.
Large Language Model Transformers
A
TheBloke
22
8
Lzlv 70b Fp16 Hf
A specialized model for roleplay and creative work, fine-tuned from multiple LLaMA2 70B models, combining features from Nous-Hermes-Llama2-70b, Xwin-LM-7B-V0.1, and Mythospice-70b
Large Language Model Transformers
L
lizpreciatior
144
75
Wav2vec2 Large Xlsr 53 Tw Gpt
Apache-2.0
A speech recognition model fine-tuned on Taiwan Mandarin (zh-tw) based on facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampling rate audio input
Speech Recognition Transformers
W
voidful
47
3
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase