Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
AJ-Llama33-70B-v3.0.0-GGUF – AI Model by ianwesterfield | AlphaNeural AI
You can deploy this model and start earning money today!
ianwesterfield
/
AJ-Llama33-70B-v3.0.0-GGUF
like
0
gguf
llama
fine-tuned
meta-llama/Llama-3.3-70B-Instruct
quantized
llama3.3
endpoints_compatible
us
conversational
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
AJ-Llama33-70B-v3.0.0-GGUF
GGUF quantizations of AJ v3.0.0, fine-tuned from Llama-3.3-70B-Instruct.
Available Quantizations
File
Size
Description
AJ-Llama33-70B-v3.0.0.Q8_0.gguf
~70 GB
8-bit quantization, highest quality
AJ-Llama33-70B-v3.0.0.Q6_K.gguf
~54 GB
6-bit K-quant, good balance
Training Details
Base Model
: meta-llama/Llama-3.3-70B-Instruct
Training
: LoRA fine-tuning (r=64, alpha=128)
Dataset
: mixed_v1 (279K samples, 2 epochs)
Final Step
: 34,930
Usage
Load with llama.cpp, Ollama, or any GGUF-compatible runtime.
