Model Intelligence Sheet
RockMan256/Llama-3.2-3B-Instruct-home16k-GGUF overview
Llama 3.2 3B Instruct home16k GGUF GGUF quantization of RockMan256/Llama 3.2 3B Instruct home16k https://huggingface.co/RockMan256/Llama 3.2 3B Instruct home16…
Runs locally from ~1.88 GB 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-Instruct-home16k-Q4_K_M.gguf | GGUF | Q4_K_M | 1.88 GB | Download |
Model Details
| Model ID | RockMan256/Llama-3.2-3B-Instruct-home16k-GGUF |
|---|---|
| Author | RockMan256 |
| Pipeline | — |
| License | — |
| Base model | RockMan256/Llama-3.2-3B-Instruct-home16k |
| Last modified | 2026-07-11T09:07:33.000Z |
Model README
---
base_model: RockMan256/Llama-3.2-3B-Instruct-home16k
library_name: llama-cpp
---
Llama-3.2-3B-Instruct-home16k-GGUF
GGUF quantization of RockMan256/Llama-3.2-3B-Instruct-home16k.
Converted using llama.cpp.
Files
| File | Type | Size |
|------|------|------|
| llama-3.2-3B-Instruct-home16k-Q4_K_M.gguf | Text model (Q4_K_M) | 1.92 GB |
Usage
llama.cpp CLI
./llama-server \
-m llama-3.2-3B-Instruct-home16k-Q4_K_M.gguf \
--host 0.0.0.0 --port 8080Open WebUI
- Go to Settings > Connections > Model Ollama
- Set the API URL to your llama.cpp server endpoint
- Upload
llama-3.2-3B-Instruct-home16k-Q4_K_M.gguf
Source Model
- Base: meta-llama/Llama-3.2-3B-Instruct
- Fine-tuned: RockMan256/Llama-3.2-3B-Instruct-home16k (16k context, Unsloth fine-tuned)
Run RockMan256/Llama-3.2-3B-Instruct-home16k-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models