Instructions to use second-state/xLAM-8x7b-r-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use second-state/xLAM-8x7b-r-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 second-state/xLAM-8x7b-r-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/xLAM-8x7b-r-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 second-state/xLAM-8x7b-r-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/xLAM-8x7b-r-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 second-state/xLAM-8x7b-r-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/xLAM-8x7b-r-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 second-state/xLAM-8x7b-r-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/xLAM-8x7b-r-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/xLAM-8x7b-r-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/xLAM-8x7b-r-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/xLAM-8x7b-r-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": "second-state/xLAM-8x7b-r-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/second-state/xLAM-8x7b-r-GGUF:Q4_K_M

Ollama
How to use second-state/xLAM-8x7b-r-GGUF with Ollama:
```
ollama run hf.co/second-state/xLAM-8x7b-r-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use second-state/xLAM-8x7b-r-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/xLAM-8x7b-r-GGUF:Q4_K_M
```

Lemonade

How to use second-state/xLAM-8x7b-r-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/xLAM-8x7b-r-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.xLAM-8x7b-r-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

xLAM-8x7b-r-GGUF

Original Model

Salesforce/xLAM-8x7b-r

Run with LlamaEdge

LlamaEdge version: coming soon

Context size: 32000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
xLAM-8x7b-r-Q2_K.gguf	Q2_K	2	17.3 GB	smallest, significant quality loss - not recommended for most purposes
xLAM-8x7b-r-Q3_K_L.gguf	Q3_K_L	3	24.2 GB	small, substantial quality loss
xLAM-8x7b-r-Q3_K_M.gguf	Q3_K_M	3	22.5 GB	very small, high quality loss
xLAM-8x7b-r-Q3_K_S.gguf	Q3_K_S	3	20.4 GB	very small, high quality loss
xLAM-8x7b-r-Q4_0.gguf	Q4_0	4	26.4 GB	legacy; small, very high quality loss - prefer using Q3_K_M
xLAM-8x7b-r-Q4_K_M.gguf	Q4_K_M	4	28.4 GB	medium, balanced quality - recommended
xLAM-8x7b-r-Q4_K_S.gguf	Q4_K_S	4	26.7 GB	small, greater quality loss
xLAM-8x7b-r-Q5_0.gguf	Q5_0	5	32.2 GB	legacy; medium, balanced quality - prefer using Q4_K_M
xLAM-8x7b-r-Q5_K_M.gguf	Q5_K_M	5	33.2 GB	large, very low quality loss - recommended
xLAM-8x7b-r-Q5_K_S.gguf	Q5_K_S	5	32.2 GB	large, low quality loss - recommended
xLAM-8x7b-r-Q6_K.gguf	Q6_K	6	38.4 GB	very large, extremely low quality loss
xLAM-8x7b-r-Q8_0.gguf	Q8_0	8	49.6 GB	very large, extremely low quality loss - not recommended
xLAM-8x7b-r-f16-00001-of-00004.gguf	f16	16	29.4 GB
xLAM-8x7b-r-f16-00002-of-00004.gguf	f16	16	30.0 GB
xLAM-8x7b-r-f16-00003-of-00004.gguf	f16	16	29.3 GB
xLAM-8x7b-r-f16-00004-of-00004.gguf	f16	16	4.78 GB

Quantized with llama.cpp b3613.

Downloads last month: 128

GGUF

Model size

47B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for second-state/xLAM-8x7b-r-GGUF

Base model

Salesforce/xLAM-8x7b-r

Quantized

(8)

this model