Downloads · 30 days
51
12% of all-time downloads
CelesteImperia/Llama-3-70B-Instruct-Platinum-GGUF
Llama-3-70B-Instruct-Platinum-GGUF is a text generation model from CelesteImperia. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as llama3.
Downloads · 30 days
51
12% of all-time downloads
All-time downloads
420
Public
Repo size
210 GB
Likes
0
Public
Click a slice to open those files.
.gguf210 GB · 100%
From the Hugging Face model README
This repository contains the Platinum Series universal GGUF release of Llama-3-70B-Instruct. This collection provides professional-grade quantization levels optimized for high-fidelity reasoning and complex financial analysis, offering a massive intelligence boost for local workstations while maintaining exceptional stability on multi-GPU hardware.
| File | Method | Description |
|---|---|---|
| Q3_K_M | k-quant | Significant compression for maximum speed and lower VRAM footprints. |
| Q4_K_M | k-quant | The Gold Standard. Optimal balance of logic retention and inference speed. |
| Q6_K | k-quant | High-bit precision for complex document analysis and financial reasoning. |
| Q8_0 | block-quant | The "Teacher" alternative. Near-perfect fidelity to the original F16 master. |
To run these engines using the provided python script :
from llama_cpp import Llama
# Initialize the model
llm = Llama(
model_path="./Llama-3-70B-Instruct-Q4_K_M.gguf",
n_gpu_layers=-1, # Offload all layers to VRAM
n_ctx=8192, # Context window
)
# Generate response
output = llm(
"Analyze the current trends in the Indian stock market for 2026.",
max_tokens=512,
stop=["<|eot_id|>"],
echo=True
)
print(output['choices'][0]['text'])
This collection is fully compatible with .NET applications via the csharp script and the LLamaSharp library.
using LLama.Common;
using LLama;
var parameters = new ModelParams("Llama-3-70B-Instruct-Q4_K_M.gguf")
{
ContextSize = 8192,
GpuLayerCount = -1 // Utilize all available CUDA cores
};
using var weights = LLamaWeights.LoadFromFile(parameters);
using var context = weights.CreateContext(parameters);
var executor = new InteractiveExecutor(context);
var chatHistory = new ChatHistory();
chatHistory.AddMessage(AuthorRole.System, "You are a helpful assistant.");
chatHistory.AddMessage(AuthorRole.User, "Hello!");
var session = new ChatSession(executor, chatHistory);
await foreach (var text in session.ChatAsync(new ChatHistory.Message(AuthorRole.User, "Explain GST impact on small businesses."), new InferenceParams { MaxTokens = 1024 }))
{
Console.Write(text);
}
Given the 70B parameter count, the following configurations are recommended:
Maintaining the production line for high-fidelity models requires significant hardware resources. If these tools power your research or industrial projects, please consider supporting the development:
| Platform | Support Link |
|---|---|
| Global & India | Support via Razorpay |
Scan to support via UPI (India Only):
<img src="https://huggingface.co/datasets/CelesteImperia/Assets/resolve/main/QrCode.jpeg" width="200">Connect with the architect: Abhishek Jaiswal on LinkedIn