Downloads · 30 days
102
5% of all-time downloads
llama-3.2-3b-instruct-gguf
neopolita/llama-3.2-3b-instruct-gguf
llama-3.2-3b-instruct-gguf is a machine learning model from neopolita. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Terms of Use: Please check the original model
All-time downloads
2.1K
Public
Repo size
19.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf19.9 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 25, 2024
- Updated
- Sep 25, 2024
- SHA
- b538511d
Model card
From the Hugging Face model README
GGUF quants for meta-llama/Llama-3.2-3B-Instruct using llama.cpp
Terms of Use: Please check the original model
<picture> <img alt="cthulhu" src="https://huggingface.co/neopolita/common/resolve/main/profile.png"> </picture>Quants
q2_k: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors.q3_k_s: Uses Q3_K for all tensorsq3_k_m: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_Kq3_k_l: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_Kq4_0: Original quant method, 4-bit.q4_1: Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.q4_k_s: Uses Q4_K for all tensorsq4_k_m: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_Kq5_0: Higher accuracy, higher resource usage and slower inference.q5_1: Even higher accuracy, resource usage and slower inference.q5_k_s: Uses Q5_K for all tensorsq5_k_m: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_Kq6_k: Uses Q8_K for all tensorsq8_0: Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.
- Created
- Sep 25, 2024
- Updated
- Sep 25, 2024