Home/Models/neuralmagic/Llama-3.2-3B-Instruct-quantized.w8a8
Llama-3.2-3B-Instruct-quantized.w8a8
neuralmagic/Llama-3.2-3B-Instruct-quantized.w8a8
- kind
- original
- quant
- bf16 (16-bit)
- family
- llama
- modality
- text-generation
- root model
- meta-llama/Llama-3.2-3B-Instruct
- provider
- neuralmagic
- license
- llama3.2
- language
- en, de, fr, it, pt, hi, es, th
- context
- —
- library
- —
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 464
- likes
- 0
- created
- —
- last modified
- 2025-07-09T23:57:45+00:00 (2025)
- huggingface
- https://huggingface.co/neuralmagic/Llama-3.2-3B-Instruct-quantized.w8a8
- tags
- safetensorsllamallama-3neuralmagicllmcompressortext-generationconversationalendefritpthiestharxiv:2211.10438arxiv:2210.17323base_model:meta-llama/Llama-3.2-3B-Instructbase_model:quantized:meta-llama/Llama-3.2-3B-Instructlicense:llama3.28-bitcompressed-tensorsregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.