Instructions to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
Use Docker
docker model run hf.co/sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
- SGLang
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with Ollama:
ollama run hf.co/sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with Docker Model Runner:
docker model run hf.co/sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
- Lemonade
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Llama-3.2-3B-TechWriter-Instruct-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Llama-3.2-3B TechWriter Instruct GGUF
This repository provides GGUF quantizations for Shankarblr/Llama-3.2-3B-TechWriter-Instruct.
Llama-3.2-3B TechWriter is a fine-tune of meta-llama/Llama-3.2-3B-Instruct specialized for semiconductor and data-center interconnect technical documentation, product briefs, datasheets, application notes, and CLI user guides.
All GGUF files were converted from the original safetensors weights using llama.cpp at native F16 precision, followed by quantization into standard k-quant variants.
Available Files and Quantizations
| File | Quant Type | Size | Description / Recommendation |
|---|---|---|---|
Llama-3.2-3B-TechWriter-Instruct-F16.gguf |
F16 | 5.99 GB | Full precision base conversion. Highest fidelity reference weights. |
Llama-3.2-3B-TechWriter-Instruct-Q8_0.gguf |
Q8_0 | 3.19 GB | Near-lossless 8-bit quantization. Recommended for best quality. |
Llama-3.2-3B-TechWriter-Instruct-Q6_K.gguf |
Q6_K | 2.46 GB | High quality retention with minimal degradation. Excellent balance. |
Llama-3.2-3B-TechWriter-Instruct-Q5_K_M.gguf |
Q5_K_M | 2.16 GB | Solid balance between memory usage and generation accuracy. |
Llama-3.2-3B-TechWriter-Instruct-Q4_K_M.gguf |
Q4_K_M | 1.88 GB | Fast, lightweight 4-bit quant. Recommended default for mobile and edge setups. |
Llama-3.2-3B-TechWriter-Instruct-Q3_K_M.gguf |
Q3_K_M | 1.57 GB | Compact footprint when memory headroom is strictly limited. |
Llama-3.2-3B-TechWriter-Instruct-Q2_K.gguf |
Q2_K | 1.27 GB | Maximum compression for ultra-constrained environments. |
Domain Capabilities
This model is fine-tuned to produce structured, consistent technical documentation:
- Product Briefs & Datasheets: Feature summaries, pinout descriptions, electrical specs, and register descriptions.
- Hardware & CLI Documentation: Host-adapter (HBA/NIC), switch, and DPU command-line user manuals.
- Architecture Notes: Process node, throughput, bus width, and protocol stack consistency.
- Spec Extraction: Grounded extraction and QA from raw hardware documentation excerpts.
Prompt Format
This model uses the standard Llama 3.2 Instruct template format:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a technical marketing and documentation writer for semiconductor and data-center interconnect products. Write clear, structured content. Match the requested document type. Keep specifications internally consistent: one process node, one primary throughput, and one form factor unless the source explicitly lists options.<|eot_id|><|start_header_id|>user<|end_header_id|>
Write a short feature overview for a 400G PCIe Gen5 NIC.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
How to Use
1. With llama.cpp
Run interactive or single-turn generation with llama-cli:
llama-cli -m ./Llama-3.2-3B-TechWriter-Instruct-Q4_K_M.gguf \
-p "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful technical writer.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWrite a short paragraph explaining what an API endpoint is.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" \
-n 256 --temp 0.2
Launch a local OpenAI-compatible HTTP server:
llama-server -m ./Llama-3.2-3B-TechWriter-Instruct-Q4_K_M.gguf \
--host 127.0.0.1 --port 8080 -c 4096
2. With Ollama
Create a Modelfile:
FROM ./Llama-3.2-3B-TechWriter-Instruct-Q4_K_M.gguf
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ .Response }}<|eot_id|>"""
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
PARAMETER temperature 0.3
Then create and run the model:
ollama create techwriter-3b -f Modelfile
ollama run techwriter-3b
3. With LM Studio
- Copy the desired
.gguffile (e.g.,Llama-3.2-3B-TechWriter-Instruct-Q4_K_M.gguf) into your LM Studio models directory. - Select Llama 3 as the chat preset.
- Load the model and begin prompting.
- Downloads last month
- 230
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Model tree for sizzlebop/Llama-3.2-3B-TechWriter-Instruct-GGUF
Base model
meta-llama/Llama-3.2-3B-Instruct