Model Intelligence Sheet
vvnaren/LLAMA-3.2-3B-MathInstruct_LORA_SFT-Q8_0-GGUF overview
vvnaren/LLAMA 3.2 3B MathInstruct LORA SFT Q8 0 GGUF This LoRA adapter was converted to GGUF format from SriSanthM/LLAMA 3.2 3B MathInstruct LORA SFT https://h…
Runs locally from ~17.9 MB disk (4 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 |
|---|---|---|---|---|
| LLAMA-3.2-3B-MathInstruct_LORA_SFT-q8_0.gguf | GGUF | Q8_0 | 17.9 MB | Download |
Model Details
Model README
---
datasets:
- TIGER-Lab/MathInstruct
base_model: SriSanthM/LLAMA-3.2-3B-MathInstruct_LORA_SFT
tags:
- lora
- adapters
- llama
- llama-cpp
- gguf-my-lora
---
vvnaren/LLAMA-3.2-3B-MathInstruct_LORA_SFT-Q8_0-GGUF
This LoRA adapter was converted to GGUF format from SriSanthM/LLAMA-3.2-3B-MathInstruct_LORA_SFT via the ggml.ai's GGUF-my-lora space.
Refer to the original adapter repository for more details.
Use with llama.cpp
# with cli
llama-cli -m base_model.gguf --lora LLAMA-3.2-3B-MathInstruct_LORA_SFT-q8_0.gguf (...other args)
# with server
llama-server -m base_model.gguf --lora LLAMA-3.2-3B-MathInstruct_LORA_SFT-q8_0.gguf (...other args)To know more about LoRA usage with llama.cpp server, refer to the llama.cpp server documentation.
Run vvnaren/LLAMA-3.2-3B-MathInstruct_LORA_SFT-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