Instructions to use sunil-pathak/gemma-3n-E2B-it-Q6_K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use sunil-pathak/gemma-3n-E2B-it-Q6_K 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 sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K
# Run inference directly in the terminal:
llama cli -hf sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K
# Run inference directly in the terminal:
llama cli -hf sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K

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 sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K

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 sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K

Use Docker

docker model run hf.co/sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K

LM Studio
Jan

vLLM

How to use sunil-pathak/gemma-3n-E2B-it-Q6_K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sunil-pathak/gemma-3n-E2B-it-Q6_K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sunil-pathak/gemma-3n-E2B-it-Q6_K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K

Ollama
How to use sunil-pathak/gemma-3n-E2B-it-Q6_K with Ollama:
```
ollama run hf.co/sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K
```
Unsloth Desktop
Docker Model Runner
How to use sunil-pathak/gemma-3n-E2B-it-Q6_K with Docker Model Runner:
```
docker model run hf.co/sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K
```

Lemonade

How to use sunil-pathak/gemma-3n-E2B-it-Q6_K with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sunil-pathak/gemma-3n-E2B-it-Q6_K:Q6_K

Run and chat with the model

lemonade run user.gemma-3n-E2B-it-Q6_K-Q6_K

List all available models

lemonade list

Atomic Chat

sunil-pathak commited on Apr 19

Commit

0d0ba7b

verified ·

1 Parent(s): 8144785

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -16,9 +16,10 @@ pipeline_tag: text-generation
 ## 📊 Performance Metrics
 - **Size:** 3.47 GB
-- **Speed (Generation):** 5.22 tokens/sec
-- **Speed (Prompt):** 10.85 tokens/sec
 - **KV Cache Usage:** 0.0143 GB
 - **Quantization:** Q6_K
@@ -31,7 +32,7 @@ This repository contains a **GGUF quantized version** of:
 - **Base Model:** gemma-3n-E2B-it
 - **Format:** GGUF (optimized for llama.cpp inference)
 - **Precision:** Q6_K
-- **Efficiency Score:** 1.5055 (TPS/GB)
 GGUF format provides:
 - Fast loading via memory mapping
@@ -57,7 +58,8 @@ GGUF format provides:
 | Format | GGUF |
 | Precision | Q6_K |
 | Runtime | llama.cpp |
-| Context Latency | 28.58s |
 | Memory (KV) | 0.0143 GB |
 ---

 ## 📊 Performance Metrics
+- **Hardware:** Intel(R) Xeon(R) CPU @ 2.20GHz (4 vCPUs)
 - **Size:** 3.47 GB
+- **Speed (Generation):** 5.41 tokens/sec
+- **Speed (Prompt):** 10.76 tokens/sec
 - **KV Cache Usage:** 0.0143 GB
 - **Quantization:** Q6_K
 - **Base Model:** gemma-3n-E2B-it
 - **Format:** GGUF (optimized for llama.cpp inference)
 - **Precision:** Q6_K
+- **Efficiency Score:** 1.5603 (TPS/GB)
 GGUF format provides:
 - Fast loading via memory mapping
 | Format | GGUF |
 | Precision | Q6_K |
 | Runtime | llama.cpp |
+| Benchmark Hardware | Intel(R) Xeon(R) CPU @ 2.20GHz (4 vCPUs) |
+| Context Latency | 29.69s |
 | Memory (KV) | 0.0143 GB |
 ---