# English Generation

QWEN 3B INSTRUC Medical COT SFT 2kstep 4kcol
Apache-2.0
A 3B parameter instruction fine-tuned model based on Qwen2.5 architecture, optimized for training speed using Unsloth and Huggingface TRL library
Large Language Model Transformers English
Q
hailong18102002
30
1
Gemma 2 9b It Abliterated GGUF
A quantized version based on Gemma 2.9B, optimized using llama.cpp, suitable for running in LM Studio.
Large Language Model English
G
bartowski
3,941
37
Space Voice Label Detect Beta
Apache-2.0
Fine-tuned version based on Qwen2.5-VL-3B model, trained using Unsloth and Huggingface TRL library, achieving 2x inference speed improvement
Text-to-Image Transformers English
S
devJy
38
1
Sales Conversations Unsloth Llama 3.1 8B Instruct
Apache-2.0
4-bit quantized version based on Meta-Llama-3.1-8B-Instruct, efficiently trained using Unsloth and TRL libraries
Large Language Model Transformers English
S
vakodiya
22
1
Meta Llama 3 70B Instruct AWQ
Other
Meta-Llama-3-70B-Instruct is a 70B parameter-scale instruction-tuned large language model released by Meta, optimized for dialogue use cases, with outstanding performance in safety and helpfulness.
Large Language Model Transformers English
M
TechxGenus
210
12
Meta Llama 3 8B Instruct GGUF
This is the GGUF quantized version of the 8 billion parameter instruction-tuned model from the Meta Llama 3 series, optimized for dialogue scenarios and demonstrating excellent performance in multiple benchmark tests.
Large Language Model English
M
MaziyarPanahi
293.90k
88
Llama
Llama 2 is a 70-billion-parameter conversation-optimized large language model developed by Meta, surpassing most open-source dialogue models in benchmark tests with safety comparable to mainstream proprietary models
Large Language Model Transformers English
L
TheCraftySlayer
48
1
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase