π§
Phi 4 Quantized.w8a8 model by RedHatAI
β 55.3
π¬Technical Deep Dive
Full Specifications [+]
π Updated daily
Source summary: Based on Hugging Face metadata. Not a recommendation.
π‘οΈ Model Transparency Report
Technical metadata sourced from upstream repositories.
Open Metadata
π Identity & Source
- id
- hf-model--redhatai--phi-4-quantized.w8a8
- slug
- redhatai--phi-4-quantized.w8a8
- source
- huggingface
- author
- RedHatAI
- license
- MIT
- tags
- safetensors, phi3, phi, nlp, math, code, chat, conversational, neuralmagic, redhat, llmcompressor, quantized, w8a8, int8, compressed-tensors, text-generation, en, arxiv:2211.10438, arxiv:2210.17323, base_model:microsoft/phi-4, base_model:quantized:microsoft/phi-4, license:mit, 8-bit, region:us
βοΈ Technical Specs
- architecture
- Phi3ForCausalLM
- params billions
- 14.66
- context length
- 4,096
- pipeline tag
- text-generation
- vram gb
- 12.3
- vram is estimated
- true
- vram formula
- VRAM β (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)
π Engagement & Metrics
- downloads
- 11,200
- stars
- null
- forks
- null
Data indexed from public sources. Updated daily.