Model Intelligence Sheet
MRockatansky/Precog-Maxxed-31B-GGUF overview
MRockatansky/Precog-Maxxed-31B-GGUF GGUF downloads for local AI inference with guIDE.
Runs locally from ~12.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
6 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Precog-Maxxed-31B-IQ4_XS.gguf | GGUF | IQ4_XS | 15.74 GB | Download |
| Precog-Maxxed-31B-Q4_K_L.gguf | GGUF | Q4_K_L | 18.14 GB | Download |
| Precog-Maxxed-31B-f16.gguf | GGUF | F16 | 58.41 GB | Download |
| loras/cogidonia-lora-f16.gguf | GGUF | F16 | 176.3 MB | Download |
| loras/precog-maxed-imat.gguf | GGUF | GGUF | 12.9 MB | Download |
| loras/skyfall-lora-f16.gguf | GGUF | F16 | 238.0 MB | Download |
Model Details
| Model ID | MRockatansky/Precog-Maxxed-31B-GGUF |
|---|---|
| Author | MRockatansky |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | MRockatansky/Precog-Magnum-31B |
| Last modified | 2026-06-21T19:18:56.000Z |
Model README
---
license: apache-2.0
pipeline_tag: text-generation # Specify the task
library_name: transformers # Specify the library
datasets:
- MRockatansky/LitBench-DPO # List datasets used for training
base_model: MRockatansky/Precog-Magnum-31B
quantized_by: MRockatansky
---
Run MRockatansky/Precog-Maxxed-31B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models