Instructions to use afrideva/Zephyr-3.43B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use afrideva/Zephyr-3.43B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="afrideva/Zephyr-3.43B-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("afrideva/Zephyr-3.43B-GGUF", dtype="auto")

llama-cpp-python

How to use afrideva/Zephyr-3.43B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="afrideva/Zephyr-3.43B-GGUF",
	filename="zephyr-3.43b.fp16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use afrideva/Zephyr-3.43B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf afrideva/Zephyr-3.43B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/Zephyr-3.43B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf afrideva/Zephyr-3.43B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/Zephyr-3.43B-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 afrideva/Zephyr-3.43B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/Zephyr-3.43B-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 afrideva/Zephyr-3.43B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/Zephyr-3.43B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/Zephyr-3.43B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/Zephyr-3.43B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afrideva/Zephyr-3.43B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/Zephyr-3.43B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/afrideva/Zephyr-3.43B-GGUF:Q4_K_M

SGLang

How to use afrideva/Zephyr-3.43B-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 "afrideva/Zephyr-3.43B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/Zephyr-3.43B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "afrideva/Zephyr-3.43B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/Zephyr-3.43B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use afrideva/Zephyr-3.43B-GGUF with Ollama:
```
ollama run hf.co/afrideva/Zephyr-3.43B-GGUF:Q4_K_M
```

Unsloth Studio

How to use afrideva/Zephyr-3.43B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for afrideva/Zephyr-3.43B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for afrideva/Zephyr-3.43B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for afrideva/Zephyr-3.43B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use afrideva/Zephyr-3.43B-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/Zephyr-3.43B-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/Zephyr-3.43B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/Zephyr-3.43B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Zephyr-3.43B-GGUF-Q4_K_M

List all available models

lemonade list

Aryanne/Zephyr-3.43B-GGUF

Quantized GGUF model files for Zephyr-3.43B from Aryanne

Name	Quant method	Size
zephyr-3.43b.fp16.gguf	fp16	6.86 GB
zephyr-3.43b.q2_k.gguf	q2_k	1.46 GB
zephyr-3.43b.q3_k_m.gguf	q3_k_m	1.70 GB
zephyr-3.43b.q4_k_m.gguf	q4_k_m	2.09 GB
zephyr-3.43b.q5_k_m.gguf	q5_k_m	2.44 GB
zephyr-3.43b.q6_k.gguf	q6_k	2.82 GB
zephyr-3.43b.q8_0.gguf	q8_0	3.65 GB

Original Model Card:

This model is a merge/fusion of Aryanne/Astridboros-3B and stabilityai/stablelm-zephyr-3b , 28 layers of Zephyr + 12 layers of Astridboros together(see zephyr-3.43b.yml or below).

A total of 40 layers, with 3.43B of parameters.

License it's the same as Zephyr cause it has 70% of it.

slices:
  - sources:
    - model: stabilityai/stablelm-zephyr-3b
      layer_range: [0, 14] 
  - sources:
    - model: Aryanne/Astridboros-3B
      layer_range: [10, 22]
  - sources:
    - model: stabilityai/stablelm-zephyr-3b
      layer_range: [18, 32]
merge_method: passthrough
dtype: float16

I recommend the use of the Zephyr prompt format.

<|user|>
List 3 synonyms for the word "tiny"<|endoftext|>
<|assistant|>
1. Dwarf
2. Little
3. Petite<|endoftext|>

GGUF Quants: [notyet](not yet)

Downloads last month: 70

GGUF

Model size

3B params

Architecture

stablelm

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for afrideva/Zephyr-3.43B-GGUF

Base model

Aryanne/Zephyr-3.43B

Quantized

(1)

this model