Instructions to use smalinin/DeepSeek-V4.1-Flash-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 smalinin/DeepSeek-V4.1-Flash-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 smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_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 smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_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 smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K

Use Docker

docker model run hf.co/smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use smalinin/DeepSeek-V4.1-Flash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smalinin/DeepSeek-V4.1-Flash-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": "smalinin/DeepSeek-V4.1-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K

Ollama
How to use smalinin/DeepSeek-V4.1-Flash-GGUF with Ollama:
```
ollama run hf.co/smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K
```
Unsloth Desktop

How to use smalinin/DeepSeek-V4.1-Flash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K

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": "smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use smalinin/DeepSeek-V4.1-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K
```

Lemonade

How to use smalinin/DeepSeek-V4.1-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K

Run and chat with the model

lemonade run user.DeepSeek-V4.1-Flash-GGUF-Q2_K

List all available models

lemonade list

Hermes Agent

How to use smalinin/DeepSeek-V4.1-Flash-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 smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K

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 smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use smalinin/DeepSeek-V4.1-Flash-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K

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 "smalinin/DeepSeek-V4.1-Flash-GGUF:Q2_K" \
  --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"

DeepSeek-V4.1-Flash-GGUF / README.md

smalinin

Update README.md

9257530 verified 2 days ago

preview code

Raw

History Blame Contribute Delete

1.83 kB

metadata

license: mit
base_model: deepseek-ai/DeepSeek-V4.1-Flash
base_model_relation: quantized
library_name: gguf
pipeline_tag: text-generation
tags:
  - gguf
  - deepseek
  - deepseek-v4.1
  - llama.cpp
quantized_by: vcruz305
quality recovered: smalinin

DeepSeek-V4.1-Flash GGUF

llama.cpp GGUF of deepseek-ai/DeepSeek-V4.1-Flash.

This is V4.1-Flash (DeepseekV41ForCausalLM), a causal decoder with engram n-gram lookup tables, hyper-connections and sparse attention. It is not V4-Flash-0731.

Recipe

How to build the engine, serve it, and the gotchas, plus the current status: https://github.com/smalinin/llama.cpp/tree/my_build_deepseek41

New runtime binary was tested on 4xRTX4090(48Gb) + 2xRTX3090 with next config:

./llama-server \
  --model ./DeepSeek-V4.1-Flash-Q2_K-00001-of-00007.gguf \
  --host 127.0.0.1 \
  --port 8080 \
  --ctx-size 64000 \
  --batch-size 2048 \
  --ubatch-size 256 \
  --parallel 1 \
  --n-gpu-layers auto \
  --fit on \
  --fit-ctx 64000 \
  --fit-target 2048 \
  --load-mode mmap \
  --lazy-mode auto \
  --flash-attn on \
  --no-warmup \
  --no-context-shift \
  --jinja \
  --chat-template-file ./models/templates/deepseek-ai-DeepSeek-V4.1.jinja \
  --chat-template-kwargs '{"reasoning_effort":80,"enable_thinking":true}' \
  --reasoning-format deepseek \
  --no-reasoning-preserve \
  --no-prefill-assistant

Results: pp = 250 t/s; tg = 4.7t/s for prompt size=25k

Status

These files do not run on upstream llama.cpp yet.

Files

Sample of Q2 work

Sample of Q4 work

Apache/MIT from upstream.