Instructions to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-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 prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-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 prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-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 prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-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 prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-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": "prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-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 "prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF" \
    --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": "prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF",
		"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 "prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF" \
        --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": "prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF: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": "prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF: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 prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF: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 "prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF: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"

JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF

Mellum2.1 Thinking is JetBrains' updated reasoning model, a 12B-parameter mixture-of-experts with 2.5B active parameters (28 layers, 64 experts with 8 active, 131,072-token context, Apache 2.0). It is the successor to Mellum2 Thinking with the architecture unchanged, and nearly all of the improvement comes from post-training, where reinforcement learning grew from a short final stage into the main part of training. It uses new RL tasks in math, competitive programming, science, tool use, and software engineering, each source filtered before training. For software engineering, it trained in real repositories with a shell and file-editing tools, rewarded when tests pass, over millions of sandboxed runs. The gains are largest on agentic work: SWE-bench Verified rises from 2.0 to 47.0, Terminal-Bench 2.1 from 0.6 to 17.4, and SWE-bench Pro from 0.0 to 28.0. LiveCodeBench v6 climbs from 69.4 to 82.0, AIME 25/26 from 60.1 to 83.3, and BFCL v4 from 49.6 to 62.3. Against Qwen3.5-9B it leads on LiveCodeBench v6 (82.0 vs 75.4), HumanEval+, MBPP+, BFCL v4 and WorkBench, but trails on AIME, GPQA Diamond (64.6 vs 77.8), SWE-bench Verified and Pro, Terminal-Bench 2.1, and IFEval. Safety results are mixed: HarmBench harmful rate improves from 21.5 to 8.5, but XSTest safe compliance slips from 91.2 to 88.8. All numbers are self-reported by JetBrains, from a shared pipeline in thinking mode. It is intended for complex agentic tasks and hard coding, math, and reasoning problems, and is served via vLLM with the qwen3 reasoning parser and optional Hermes-style tool calling.

Model Files

File Name	Quant Type	File Size	File Link	Description
Mellum2.1-12B-A2.5B-Thinking.BF16.gguf	BF16	24.3 GB	Link	Full BF16 weights. Highest quality, largest file size.
Mellum2.1-12B-A2.5B-Thinking.Q3_K_L.gguf	Q3_K_L	6.59 GB	Link	Lower quality but usable, good for low RAM availability.
Mellum2.1-12B-A2.5B-Thinking.Q3_K_M.gguf	Q3_K_M	6.33 GB	Link	Low quality.
Mellum2.1-12B-A2.5B-Thinking.Q4_K_M.gguf	Q4_K_M	8.07 GB	Link	Good quality, default size for most use cases, recommended.
Mellum2.1-12B-A2.5B-Thinking.Q4_K_S.gguf	Q4_K_S	7.4 GB	Link	Slightly lower quality with more space savings, recommended.
Mellum2.1-12B-A2.5B-Thinking.Q5_K_M.gguf	Q5_K_M	9.21 GB	Link	High quality, recommended.
Mellum2.1-12B-A2.5B-Thinking.Q5_K_S.gguf	Q5_K_S	8.63 GB	Link	High quality, recommended.
Mellum2.1-12B-A2.5B-Thinking.Q6_K.gguf	Q6_K	10.9 GB	Link	Very high quality, near perfect, recommended.