Instructions to use emperorofrome/Spark-X2.6-4B-GMCE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emperorofrome/Spark-X2.6-4B-GMCE with Transformers:

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

pipe = pipeline("text-generation", model="emperorofrome/Spark-X2.6-4B-GMCE", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("emperorofrome/Spark-X2.6-4B-GMCE", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use emperorofrome/Spark-X2.6-4B-GMCE 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 emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M

Use Docker

docker model run hf.co/emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use emperorofrome/Spark-X2.6-4B-GMCE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "emperorofrome/Spark-X2.6-4B-GMCE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emperorofrome/Spark-X2.6-4B-GMCE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M

SGLang

How to use emperorofrome/Spark-X2.6-4B-GMCE 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 "emperorofrome/Spark-X2.6-4B-GMCE" \
    --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": "emperorofrome/Spark-X2.6-4B-GMCE",
		"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 "emperorofrome/Spark-X2.6-4B-GMCE" \
        --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": "emperorofrome/Spark-X2.6-4B-GMCE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use emperorofrome/Spark-X2.6-4B-GMCE with Ollama:
```
ollama run hf.co/emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M
```
Unsloth Desktop

How to use emperorofrome/Spark-X2.6-4B-GMCE with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf emperorofrome/Spark-X2.6-4B-GMCE: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": "emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use emperorofrome/Spark-X2.6-4B-GMCE with Docker Model Runner:
```
docker model run hf.co/emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M
```

Lemonade

How to use emperorofrome/Spark-X2.6-4B-GMCE with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M

Run and chat with the model

lemonade run user.Spark-X2.6-4B-GMCE-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use emperorofrome/Spark-X2.6-4B-GMCE with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf emperorofrome/Spark-X2.6-4B-GMCE: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 emperorofrome/Spark-X2.6-4B-GMCE:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use emperorofrome/Spark-X2.6-4B-GMCE with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf emperorofrome/Spark-X2.6-4B-GMCE: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 "emperorofrome/Spark-X2.6-4B-GMCE: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"

Spark-X2.6-4B-GMCE (GMCoder Efficiency)

XHToken/Spark-X2.6-4B fine-tuned for GMCoder Efficiency, which cuts how many tokens the model spends reasoning before it answers. Files: GGUF (Q8_0, Q6_K, Q5_K_M, Q4_K_M, BF16) and BF16 safetensors.

GGUF needs llama.cpp release b11454 or newer (spark2_5 support). Run llama-server with --jinja so the chat template's enable_thinking / reasoning_effort options work. The safetensors use the base model's remote code, so load them with trust_remote_code=True.

What it does (measured)

Single run per model, one grader (blind to model identity), approximate scores, so differences of about 5 points are noise. Our own unseen "Form B" exams, 60k token cap, both models at their default setting (the base template defaults to high reasoning effort).

	Ultimate (/25)	Historical (/100, approx)	Historical tokens	Total tokens, 3 exams
Spark-X2.6-4B base, default	0 (hit 60k cap, no answer)	~84.5	35.9k	155.9k
Spark-X2.6-4B-GMCE	19.5 (finished at 43.1k)	~70.5	5.9k (-84%)	109.0k (-30%)

On Ultimate (25 math/logic questions) the base thought until the cap and never wrote an answer; GMCE's shorter reasoning finished and scored 19.5/25.
On Historical, GMCE used 84% fewer tokens but scored about 14 points lower.
On Everyday, both the base and GMCE ran to the 60k cap without answering. This model family tends to keep re-drafting on that exam in thinking mode, and GMCE does not fix it.

Caveats

This is a trade: much less reasoning for some accuracy on the exam where the base did finish.
The base with thinking turned off (enable_thinking=false) also uses few tokens (about 7k on Historical and Everyday), but it still never answered Ultimate within the cap.
Benchmarks are our own and small, one run each. Do not read the numbers as leaderboard results.

Training

QLoRA (NF4) with LoRA r8 / alpha 8 on q_k_v_proj, out_proj, g_proj, gate_proj, up_proj, down_proj (16.2M trainable params), LR 5e-5, batch 1, 16 epochs, completion-only loss, on the 531-example GMCoder corpus. The adapter was merged into the original BF16 base weights.

Downloads last month: 591

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for emperorofrome/Spark-X2.6-4B-GMCE

Base model

XHToken/Spark-X2.6-4B-Base

Finetuned

XHToken/Spark-X2.6-4B

Quantized

(63)

this model

Quantizations

2 models