Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
basecompute
/
Llama-3.2-3B-Instruct
like
0
Follow
Base Compute
8
Text Generation
basert
apple-silicon
quantized
License:
llama3.2
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Llama-3.2-3B-Instruct
10.9 GB
Ctrl+K
Ctrl+K
1 contributor
History:
9 commits
prabodbc
Upload Llama-3.2-3B-Instruct-cuda-q8.base with huggingface_hub
c111e66
verified
3 days ago
.gitattributes
1.8 kB
Upload Llama-3.2-3B-Instruct-cuda-q8.base with huggingface_hub
3 days ago
Llama-3.2-3B-Instruct-Q4.base
Safe
2.38 GB
xet
Re-convert with fixed rotary q/k permutation (baseRT-internal#114); NIAH-validated at 2k/8k. Q4 now uses the default-q4 quality profile (embeddings/head at higher precision).
16 days ago
Llama-3.2-3B-Instruct-Q8.base
Safe
3.32 GB
xet
Re-convert with fixed rotary q/k permutation (baseRT-internal#114); NIAH-validated at 2k/8k. Q4 now uses the default-q4 quality profile (embeddings/head at higher precision).
16 days ago
Llama-3.2-3B-Instruct-cuda-q4mix.base
Safe
1.91 GB
xet
Upload Llama-3.2-3B-Instruct-cuda-q4mix.base with huggingface_hub
3 days ago
Llama-3.2-3B-Instruct-cuda-q8.base
3.32 GB
xet
Upload Llama-3.2-3B-Instruct-cuda-q8.base with huggingface_hub
3 days ago
README.md
Safe
811 Bytes
Upload README.md with huggingface_hub
about 1 month ago
config.json
Safe
51 Bytes
Add config.json (enables HF download tracking)
about 1 month ago
