Optimised AWQ Quants for high-throughput deployments of Gemma2! Compatible with Transformers, TGI & VLLM 🤗

Hugging Quants
AI & ML interests
Optimised quants for high-throughput deployments! Compatible with Transformers, TGI & vLLM 🤗
Recent Activity
View all activity
Organization Card
Welcome to the home of exciting quantized models! We'd love to see increased adoption of powerful state-of-the-art open models, and quantization is a key component to make them work on more types of hardware.
Resources:
- Llama 3.1 Quantized Models: Optimised Quants of Llama 3.1 for high-throughput deployments! Compatible with Transformers, TGI & VLLM 🤗.
- Hugging Face Llama Recipes: A set of minimal recipes to get started with Llama 3.1.
Collections
3
Llama.cpp compatible quants for Llama 3.2 3B and 1B Instruct models.
-
hugging-quants/Llama-3.2-3B-Instruct-Q8_0-GGUF
Text Generation • Updated • 29.9k • 45 -
hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF
Text Generation • Updated • 44.9k • 19 -
hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF
Text Generation • Updated • 110k • 28 -
hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF
Text Generation • Updated • 74k • 13
models
19

hugging-quants/gemma-2-9b-it-AWQ-INT4
Text Generation
•
Updated
•
1.2k
•
6

hugging-quants/Mixtral-8x7B-Instruct-v0.1-AWQ-INT4
Text Generation
•
Updated
•
1.13k

hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF
Text Generation
•
Updated
•
74k
•
13

hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF
Text Generation
•
Updated
•
110k
•
28

hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF
Text Generation
•
Updated
•
44.9k
•
19

hugging-quants/Llama-3.2-3B-Instruct-Q8_0-GGUF
Text Generation
•
Updated
•
29.9k
•
45

hugging-quants/Meta-Llama-3.1-405B-BNB-NF4
Text Generation
•
Updated
•
122
•
2

hugging-quants/Meta-Llama-3.1-405B-Instruct-BNB-NF4
Text Generation
•
Updated
•
344
•
5

hugging-quants/Meta-Llama-3.1-405B-BNB-NF4-BF16
Text Generation
•
Updated
•
379
•
2

hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4
Text Generation
•
Updated
•
1.6k
•
37
datasets
None public yet