# Foundation-Sec-8B-GGUF

static quants of https://huggingface.co/fdtn-ai/Foundation-Sec-8B

- **Kind:** model (Hugging Face)
- **Hugging Face:** https://huggingface.co/mradermacher/Foundation-Sec-8B-GGUF
- **Owner:** mradermacher (https://forefy.com/u/hf/mradermacher)
- **Parameters:** 8.0B
- **Context:** 131072 tokens
- **License:** apache-2.0
- **Focus:** defensive
- **Architecture:** LlamaForCausalLM
- **Pinned revision:** `7fdedac4073e9b5c785c51045c7269f58215435c`
- **Page:** https://forefy.com/models/4be140b4-a1bd-5d9a-ac46-c32da17593a0
- **API (JSON):** https://forefy.com/api/asr/models/4be140b4-a1bd-5d9a-ac46-c32da17593a0

## What was done to it

- quantized (declared evidence, from fdtn-ai/Foundation-Sec-8B)

## Lineage

meta-llama/Llama-3.1-8B → fdtn-ai/Foundation-Sec-8B → mradermacher/Foundation-Sec-8B-GGUF

## Checks (repo at the pinned revision; not a behavior test)

- **Identity** [pass]: No lookalike name or conflicting provenance
- **Weights format** [pass]: GGUF only, nothing runs on load
- **Pickle files** [pass]: None.
- **Remote code** [pass]: None
- **Chat template** [info]: None shipped
- **Refusals modified** [pass]: No
- **License** [warn]: Declares apache-2.0, but derives from a llama3.1 model whose terms carry over
- **Lineage** [pass]: Derives from fdtn-ai/Foundation-Sec-8B
- **Model card** [warn]: 2 of 6, missing training data, evaluation results, intended use and limitations, description
- **GGUF headers** [pass]: 2 file(s) parsed, well-formed

## Variants

- F16 (gguf, 16.1 GB)
- Q8_0 (gguf, 8.5 GB)
- Q6_K (gguf, 6.6 GB)
- Q5_K_M (gguf, 5.7 GB)
- Q5_K_S (gguf, 5.6 GB)
- Q4_K_M (gguf, 4.9 GB)
- Q4_K_S (gguf, 4.7 GB)
- IQ4_XS (gguf, 4.5 GB)
- Q3_K_L (gguf, 4.3 GB)
- Q3_K_M (gguf, 4.0 GB)
- Q3_K_S (gguf, 3.7 GB)
- Q2_K (gguf, 3.2 GB)

## Run it

- GGUF: `ollama run hf.co/mradermacher/Foundation-Sec-8B-GGUF:Q2_K`