Home/Models/unsloth/Llama-3.2-1B-Instruct-FP8-Block
Llama-3.2-1B-Instruct-FP8-Block
unsloth/Llama-3.2-1B-Instruct-FP8-Block
- kind
- fp8
- quant
- fp8 (8-bit)
- family
- llama
- modality
- text-generation
- root model
- meta-llama/Llama-3.2-1B-Instruct
- provider
- unsloth
- license
- llama3.2
- language
- en
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 335
- likes
- 1
- created
- —
- last modified
- 2025-11-22T14:42:33+00:00 (2025)
- huggingface
- https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-FP8-Block
- tags
- transformerssafetensorsllamatext-generationllama-3metafacebookunslothconversationalenbase_model:meta-llama/Llama-3.2-1B-Instructbase_model:quantized:meta-llama/Llama-3.2-1B-Instructlicense:llama3.2text-generation-inferenceendpoints_compatiblecompressed-tensorsregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.