Model Intelligence Sheet
RaspizdAI/petuh-2.0-gguf overview
🐔 Petuh 2.0 The fastest lightweight reasoning model trained from scratch on 4.72B tokens and fine tuned on pure entropy. Technical Specifications: Total Param…
Runs locally from ~52.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
8 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| petuh-2.0-f16.gguf | GGUF | F16 | 208.3 MB | Download |
| petuh-2.0-q3_k_m.gguf | GGUF | Q3_K_M | 52.1 MB | Download |
| petuh-2.0-q4_0.gguf | GGUF | Q4_0 | 60.5 MB | Download |
| petuh-2.0-q4_k_m.gguf | GGUF | Q4_K_M | 63.4 MB | Download |
| petuh-2.0-q5_0.gguf | GGUF | Q5_0 | 72.8 MB | Download |
| petuh-2.0-q5_k_m.gguf | GGUF | Q5_K_M | 74.3 MB | Download |
| petuh-2.0-q6_k.gguf | GGUF | Q6_K | 85.8 MB | Download |
| petuh-2.0-q8_0.gguf | GGUF | Q8_0 | 110.9 MB | Download |
Model Details
Model README
---
license: mit
tags:
- petuh
- reasoning
- think
---
🐔 Petuh-2.0
The fastest lightweight reasoning model trained from scratch on 4.72B tokens and fine-tuned on pure entropy.
Technical Specifications:
- Total Parameters: 108,943,104 (~108.9M)
- Vocabulary Size: 8,192
- Embedding Dimensions: 768
- Hidden Layers: 14
- Attention Heads: 12 (Query) / 4 (KV, GQA)
- Context Length: 1,536
Benchmark Results:
| Benchmark | Score |
| :--- | :---: |
| AIME 2025 | 0.0 |
| HLE | 0.0 |
| Terminal bench 2.1 | 0.0 |
| SWE Bench verified | 0.0 |
Run RaspizdAI/petuh-2.0-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models