Model Intelligence Sheet
gghfez/Laguna-XS.2-jlens-GGUF overview
d model=2048 n prompts=200 layers=0..38 39 dtype=f16 wrote laguna bf16 jacobian lens.gguf
Runs locally from ~312.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| laguna_bf16_jacobian_lens.gguf | GGUF | BF16 | 312.0 MB | Download |
Model Details
Model README
---
base_model:
- PrimeIntellect/Laguna-XS.2-jlens
tags:
- interpretability
- jacobian-lens
---
d_model=2048 n_prompts=200 layers=0..38 (39) dtype=f16
wrote laguna_bf16_jacobian_lens.gguf
Run gghfez/Laguna-XS.2-jlens-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models