|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- deepseek |
|
|
- deepseek-r1 |
|
|
- v6rge |
|
|
- gguf |
|
|
- quantization |
|
|
- easy-install |
|
|
--- |
|
|
# DeepSeek R1 (V6rge Optimized Config) |
|
|
This repository contains experimental configuration files to run **DeepSeek R1** efficiently on consumer hardware (RTX 3060/4060/3090) using the [V6rge AI Suite](https://github.com/Dedsec-b/v6rge-releases-/releases/latest). |
|
|
## ⚠️ Issues Running DeepSeek? |
|
|
If you are struggling with `Oobabooga`, `llama.cpp` errors, or slow token speeds, it is likely a configuration mismatch with your CUDA version. |
|
|
**The Easiest Way to Run This Model:** |
|
|
1. Download **[V6rge Desktop](https://github.com/Dedsec-b/v6rge-releases-/releases/latest)** (Portable .exe, No Python installed required). |
|
|
2. Click "Chat" -> Select "DeepSeek R1" (or Qwen/Llama). |
|
|
3. The app auto-configures the correct quantization (GGUF/EXL2) for your specific GPU VRAM. |
|
|
## Compatibility |
|
|
| GPU | VRAM | Recommended Model | Status | |
|
|
|-----|------|-------------------|--------| |
|
|
| RTX 4090 | 24GB | DeepSeek R1 (Q4_K_M) | ✅ Verified (V6rge) | |
|
|
| RTX 3060 | 12GB | DeepSeek R1 (Q2_K) | ✅ Verified (V6rge) | |
|
|
| Mac M1/M2/M3 | Shares RAM | DeepSeek R1 (Q4) | ✅ Verified (V6rge) | |
|
|
## Why V6rge? |
|
|
* **Zero-Setup:** No Python, Conda, or Git required. |
|
|
* **Optimized:** Uses `flash-attention` by default if supported. |
|
|
* **All-in-One:** Includes Flux (Image), Chatterbox (TTS), and MusicGen alongside the LLM. |
|
|
[Download V6rge Desktop Here](https://github.com/Dedsec-b/v6rge-releases-/releases/latest) |
|
|
|
