# Lightweight LLM
Pythia 70m Wikipedia Paragraphs I1 GGUF
Apache-2.0
This is a quantized version based on the Pythia-70m model, specifically optimized for Wikipedia paragraph data, offering multiple quantization types to meet different resource requirements.
Large Language Model
Transformers English

P
mradermacher
823
1
Qwen3 1.7B 4bit
Apache-2.0
Qwen3-1.7B-4bit is a 4-bit quantized version of the Tongyi Qianwen 1.7B model, which has been converted to the MLX framework format for efficient operation on Apple Silicon devices.
Large Language Model
Q
mlx-community
11.85k
2
Qwen3 0.6B Base
Apache-2.0
Qwen3 is the latest generation of the Qwen series with 600 million parameters, supporting 32k context length and covering 119 languages
Large Language Model
Transformers

Q
Qwen
58.85k
44
Minicpm S 1B Sft
Apache-2.0
MiniCPM-S-1B-sft is a 1B-parameter language model optimized with activation sparsity techniques, achieving high-sparsity inference acceleration through the ProSparse method while maintaining performance comparable to the original model.
Large Language Model
Transformers Supports Multiple Languages

M
openbmb
169
10
Txgemma 27b Predict
Other
TxGemma is a series of lightweight, advanced open language models based on Gemma 2, specifically fine-tuned for therapeutic development. Available in 2B, 9B, and 27B sizes, it excels in processing information related to therapeutic modalities and targets.
Large Language Model
Transformers English

T
google
1,255
24
Txgemma 9b Chat
Other
TxGemma is a lightweight open-source language model based on Gemma 2, fine-tuned specifically for therapeutic development, available in 2B, 9B, and 27B sizes.
Large Language Model
Transformers English

T
google
4,111
31
Qwen Encoder 0.5B GGUF
Apache-2.0
This is a statically quantized version of the knowledgator/Qwen-encoder-0.5B model, primarily designed for text encoding tasks.
Large Language Model English
Q
mradermacher
175
1
Diraya 3B Instruct Ar
Apache-2.0
A Qwen2.5-3B fine-tuned Arabic reasoning-specific language model, focused on enhancing Arabic language models' capabilities in logical reasoning and mathematical problem-solving.
Large Language Model
Transformers Arabic

D
Omartificial-Intelligence-Space
86
2
Qvikhr 2.5 1.5B Instruct SMPO MLX 4bit
Apache-2.0
This is a 4-bit quantized version of the QVikhr-2.5-1.5B-Instruct-SMPO model, optimized for the MLX framework, supporting Russian and English instruction understanding and generation tasks.
Large Language Model
Transformers Supports Multiple Languages

Q
Vikhrmodels
249
2
Deepseek R1 Distill Llama 8B Abliterated
DeepSeek-R1-Distill-Llama-8B is a distilled large language model based on the Llama architecture, with a parameter scale of 8B, primarily designed for English text generation and comprehension tasks.
Large Language Model
Transformers English

D
stepenZEN
119
9
Microsoft Phi 4 GPTQ Int4
Phi-4 is an efficient small language model developed by Microsoft, focusing on high-performance inference under limited resources
Large Language Model
Transformers

M
jakiAJK
1,404
2
Dolphin3.0 Llama3.2 1B GGUF
A 1B-parameter quantized model based on Llama3.2 architecture, supporting text generation tasks with multiple quantization version options
Large Language Model English
D
bartowski
1,134
4
H2o Danube3.1 4b Chat
Apache-2.0
A chat model with 4 billion parameters fine-tuned by H2O.ai, adjusted based on the Llama 2 architecture, supporting a context length of 8192
Large Language Model
Transformers English

H
h2oai
271
5
Cotype Nano
Other
Cotype-Nano is a lightweight LLM designed to perform tasks with minimal resources. It is optimized for fast and efficient interaction with users, delivering high performance even under resource-constrained conditions.
Large Language Model
Transformers

C
MTSAIR
4,075
51
Llama 3 2 1b Sft
A fine-tuned version of the NousResearch/Llama-3.2-1B model on the ultrachat_200k dataset, focusing on dialogue task optimization.
Large Language Model
Transformers

L
wassname
637
1
Mistral Small Instruct 2409 Abliterated
Other
This is an ablated model based on mistralai/Mistral-Small-Instruct-2409, mainly used for text generation tasks.
Large Language Model
Transformers Supports Multiple Languages

M
byroneverson
11.24k
14
Llama3.1 1B Neo BAAI 1000k
Apache-2.0
Llama3.1-Neo-1B-100w is an efficient language model pruned to 1.4B parameters from Meta-Llama-3.1-8B-Instruct and fine-tuned using the LLM-Neo method (combining LoRA and knowledge distillation). The training data consists of 1 million samples from BAAI/Infinity-Instruct.
Large Language Model
Transformers

L
yang31210999
39
2
QQQ Llama 3 8b G128
MIT
This is a version of the Llama-3-8b model quantized to INT4, using the QQQ quantization technique with a group size of 128 and optimized for hardware.
Large Language Model
Transformers

Q
HandH1998
1,708
2
H2o Danube3 500m Chat
Apache-2.0
A 500M parameter dialogue fine-tuned model developed by H2O.ai, based on the Llama 2 architecture with Chinese dialogue support
Large Language Model
Transformers English

H
h2oai
3,728
36
Gemma 2 27b It
Gemma is a lightweight open-source large language model series launched by Google, built on the same technology used to create Gemini models, suitable for various text generation tasks.
Large Language Model
Transformers

G
google
160.10k
543
Tinychat 1776K
Apache-2.0
This is a small language model trained from scratch on the TinyChat dataset, aiming to achieve natural conversational responses with minimal model size.
Large Language Model
Transformers

T
raincandy-u
157
9
Orca Mini V5 8b Dpo
An 8B parameter model based on the Llama 3 architecture, trained with various DPO datasets, focused on text generation tasks
Large Language Model
Transformers English

O
pankajmathur
16
3
Llava Phi 3 Mini Gguf
LLaVA-Phi-3-mini is a fine-tuned LLaVA model based on Phi-3-mini-4k-instruct and CLIP-ViT-Large-patch14-336, specializing in image-to-text tasks.
Image-to-Text
L
xtuner
1,676
133
Llama 3 Korean Bllossom 8B
Bllossom is a Korean-English bilingual language model based on Llama3, enhanced through comprehensive tuning to improve Korean language capabilities, expanding Korean vocabulary and optimizing Korean context processing.
Large Language Model
Transformers Supports Multiple Languages

L
MLP-KTLim
26.67k
333
Wikichat V2
Apache-2.0
WikiChat-v0.2 is a dialogue model currently under training, based on OpenOrca GPT-4 data, cosmopedia, and dolly15k datasets, supporting English text generation tasks.
Large Language Model English
W
leafspark
86
2
Creek
Apache-2.0
A large language model built from scratch, with fully open-source implementations including tokenizer training, model initialization, pre-training, and instruction fine-tuning
Large Language Model
Transformers

C
maheer
21
1
Deepseek Llm Tiny Random
This is a randomly initialized small model based on the DeepSeek-LLM-67B-Chat architecture, using float16 precision, primarily for text generation tasks.
Large Language Model
Transformers

D
yujiepan
38
1
Gemma Ko 7b
Other
Gemma-Ko is a Korean large language model developed based on Google's Gemma model, offering a 7B parameter version suitable for Korean and English text generation tasks.
Large Language Model
Transformers Supports Multiple Languages

G
beomi
381
49
Tinyllava 3.1B
Apache-2.0
TinyLLaVA is a small-scale large multimodal model framework that significantly reduces the number of parameters while maintaining high performance. The 3.1B version outperforms similar 7B-scale models in multiple benchmarks.
Text-to-Image
Transformers Supports Multiple Languages

T
bczhou
184
26
Tiny Crypto Sentiment Analysis
Apache-2.0
A sentiment analysis model fine-tuned on cryptocurrency news articles using the LoRA method based on the TinyLlama model
Large Language Model
Transformers

T
curiousily
437
5
Llava Phi2
MIT
Llava-Phi2 is a multimodal implementation based on Phi2, combining vision and language processing capabilities, suitable for image-text-to-text tasks.
Image-to-Text
Transformers English

L
RaviNaik
153
6
MELT TinyLlama 1.1B Chat V1.0
Apache-2.0
A 1.1B-parameter conversational language model fine-tuned on medical data, achieving an average 13.76% improvement on medical exam benchmarks
Large Language Model
Transformers English

M
IBI-CAAI
3,010
1
Mobilellama 1.4B Base GGUF
Apache-2.0
GGUF quantized version of MobileLLaMA-1.4B-Base, suitable for local deployment and inference
Large Language Model
M
andrijdavid
311
2
Mobilellama 1.4B Base
Apache-2.0
MobileLLaMA-1.4B-Base is a Transformer model with 1.4 billion parameters, designed for out-of-the-box deployment and trained on the RedPajama v1 dataset.
Large Language Model
Transformers

M
mtgv
1,376
19
Cendol Mt5 Small Chat
Apache-2.0
Cendol mT5-small Chat is a 300-million-parameter open-source generative large language model, fine-tuned for Indonesian, Sundanese, and Javanese instructions, suitable for single-turn dialogue scenarios.
Large Language Model
Transformers Other

C
indonlp
46
3
Tinyalpaca V0.1
MIT
TinyLlama is a small language model based on the LLaMA architecture with 1.1 billion parameters, fine-tuned using the alpaca-cleaned dataset.
Large Language Model
Transformers

T
blueapple8259
85
1
Tiny Llama Miniguanaco 1.5T
Apache-2.0
The TinyLlama 1.5T checkpoint is a small language model based on 1.1B parameters, trained for answering questions.
Large Language Model
Transformers English

T
Corianas
97
3
Sheared LLaMA 2.7B
Apache-2.0
Sheared-LLaMA-2.7B is a lightweight language model derived from Llama-2-7b through pruning and continued pretraining, consuming only a 50B token budget.
Large Language Model
Transformers

S
princeton-nlp
1,131
60
Sheared LLaMA 1.3B
Apache-2.0
Sheared-LLaMA-1.3B is an efficient language model obtained through structured pruning and continual pre-training based on LLaMA-2-7B
Large Language Model
Transformers

S
princeton-nlp
11.09k
94
Chinese Llama 2 1.3b
Apache-2.0
Chinese-LLaMA-2-1.3B is a Chinese foundational model based on Meta's released Llama-2 model, expanded with a Chinese vocabulary and pre-trained in Chinese to enhance basic semantic understanding capabilities in Chinese.
Large Language Model
Transformers Supports Multiple Languages

C
hfl
1,074
19
- 1
- 2
Featured Recommended AI Models