Model Intelligence Sheet
3MPER0RR/DeepSeek-R1-Distill-Llama-8B-3MPER0RR-abliterated-Q8_0-GGUF overview
Experimental modified / abliterated versions GGUF Q8 0 version Model: DeepSeek R1 Distill Llama 8B Trials: 450 Status: Tested and saved Original model: DeepSee…
Runs locally from ~7.95 GB disk (8 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 |
|---|---|---|---|---|
| DeepSeek-R1-Distill-Llama-8B-3MPER0RR-abliterated-Q8_0.gguf | GGUF | Q8_0 | 7.95 GB | Download |
Model Details
| Model ID | 3MPER0RR/DeepSeek-R1-Distill-Llama-8B-3MPER0RR-abliterated-Q8_0-GGUF |
|---|---|
| Author | 3MPER0RR |
| Pipeline | text-generation |
| License | mit |
| Base model | 3MPER0RR/DeepSeek-R1-Distill-Llama-8B-3MPER0RR-abliterated,deepseek-ai/DeepSeek-R1-Distill-Llama-8B |
| Last modified | 2026-10-01T23:29:14.000Z |
Model README
---
license: mit
pipeline_tag: text-generation
base_model:
- 3MPER0RR/DeepSeek-R1-Distill-Llama-8B-3MPER0RR-abliterated
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
tags:
- GGUF
- Q8_0
---
Experimental modified / abliterated versions
GGUF Q8_0 version
Model: DeepSeek-R1-Distill-Llama-8B
Trials: [450]
Status: Tested and saved
Original model: DeepSeek-R1-Distill-Llama-8B
License: [Mit]
Research and experimentation by [3MPER0RR]
Run 3MPER0RR/DeepSeek-R1-Distill-Llama-8B-3MPER0RR-abliterated-Q8_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