Instructions to use paul-stansifer/qw3-gemma2-9b-1x6e-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use paul-stansifer/qw3-gemma2-9b-1x6e-4 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 paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf paul-stansifer/qw3-gemma2-9b-1x6e-4: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 paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf paul-stansifer/qw3-gemma2-9b-1x6e-4: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 paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M

Use Docker

docker model run hf.co/paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M

LM Studio
Jan

vLLM

How to use paul-stansifer/qw3-gemma2-9b-1x6e-4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "paul-stansifer/qw3-gemma2-9b-1x6e-4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paul-stansifer/qw3-gemma2-9b-1x6e-4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M

Ollama
How to use paul-stansifer/qw3-gemma2-9b-1x6e-4 with Ollama:
```
ollama run hf.co/paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use paul-stansifer/qw3-gemma2-9b-1x6e-4 with Docker Model Runner:
```
docker model run hf.co/paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M
```

Lemonade

How to use paul-stansifer/qw3-gemma2-9b-1x6e-4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull paul-stansifer/qw3-gemma2-9b-1x6e-4:Q4_K_M

Run and chat with the model

lemonade run user.qw3-gemma2-9b-1x6e-4-Q4_K_M

List all available models

lemonade list

Atomic Chat

qw3-gemma2-9b-1x6e-4 / config.json

paul-stansifer

Trained with Unsloth - config

22f0ccf verified 7 months ago

Raw

History Blame Contribute Delete

2.15 kB

	{
	"architectures": [
	"Gemma2ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_logit_softcapping": 50.0,
	"bos_token_id": 2,
	"cache_implementation": "hybrid",
	"torch_dtype": "float16",
	"eos_token_id": 1,
	"final_logit_softcapping": 30.0,
	"head_dim": 256,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 3584,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"layer_types": [
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 8192,
	"model_type": "gemma2",
	"num_attention_heads": 16,
	"num_hidden_layers": 42,
	"num_key_value_heads": 8,
	"pad_token_id": 0,
	"query_pre_attn_scalar": 256,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 10000.0,
	"sliding_window": 4096,
	"sliding_window_size": 4096,
	"unsloth_fixed": true,
	"unsloth_version": "2026.2.1",
	"use_cache": true,
	"vocab_size": 256000
	}