Instructions to use teamblobfish/DeepSeek-V4-Flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teamblobfish/DeepSeek-V4-Flash-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="teamblobfish/DeepSeek-V4-Flash-GGUF",
	filename="IQ1_M-XL/DeepSeek-V4-Flash-IQ1_M-XL-00001-of-00002.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use teamblobfish/DeepSeek-V4-Flash-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf teamblobfish/DeepSeek-V4-Flash-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 teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf teamblobfish/DeepSeek-V4-Flash-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 teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M

Use Docker

docker model run hf.co/teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use teamblobfish/DeepSeek-V4-Flash-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M

Ollama
How to use teamblobfish/DeepSeek-V4-Flash-GGUF with Ollama:
```
ollama run hf.co/teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M
```

Unsloth Studio

How to use teamblobfish/DeepSeek-V4-Flash-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for teamblobfish/DeepSeek-V4-Flash-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for teamblobfish/DeepSeek-V4-Flash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for teamblobfish/DeepSeek-V4-Flash-GGUF to start chatting

How to use teamblobfish/DeepSeek-V4-Flash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use teamblobfish/DeepSeek-V4-Flash-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf teamblobfish/DeepSeek-V4-Flash-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 teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use teamblobfish/DeepSeek-V4-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M
```

Lemonade

How to use teamblobfish/DeepSeek-V4-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-GGUF-Q4_K_M

List all available models

lemonade list

Mainline contribution?

by NeedAHugNOW - opened May 13

Discussion

NeedAHugNOW

May 13

Hi, I was just curious why a separate fork is needed for llama.cpp? Why can't these changes be contributed to base project?

cchuter

Team Blobfish org May 13

Almost ready for a PR. There are still some cuda issues to fix and llama.cpp has a strong AI stance that I’m currently navigating. I anticipate I’ll get this merged eventually

NeedAHugNOW

May 13

I have RTX A4000(ampere) and am downloading IQ2XS quant to try it right now with cpu offload.

NeedAHugNOW

29 days ago

•

edited 29 days ago

@cchuter

So i just went with Q2_K_XL quant, compiled the fork with my usual build conf and i got the following results:

RTX A4000 16gb ampere, 64gb ddr4, heavy cpu offload with --cpu-moe and heavy use of mmap:

prompt eval time = 1454933.93 ms / 17173 tokens (   84.72 ms per token,    11.80 tokens per second)
eval time =   49776.27 ms /   115 tokens (  432.84 ms per token,     2.31 tokens per second)
total time = 1504710.20 ms / 17288 tokens

I can get full 1M bf16/f16 precision context and routed experts in gpu like this. 15.4GiB vram usage.

one thing i noticed is the server fails to start if i set ubatch size to 1024, launches fine with 512.

EDIT: I noticed that the vram allocated for model seems to grow with cache as more is filled up? Like initial empty context uses say 15.4gb, but as actual context is provided, this vram allocation grows and ended up ooming at about 26k context, craahing the server.

Downtown-Case

24 days ago

•

edited 24 days ago

@NeedAHugNOW

The Q2_K_XL is ~100GB, so you must be swapping to disk with that config. I think only the IQ1_M-XL would fit without swapping (as you still need extra VRAM beyond the weights, and some RAM for the system).

NeedAHugNOW

24 days ago

@NeedAHugNOW

The Q2_K_XL is ~100GB, so you must be swapping to disk with that config. I think only the IQ1_M-XL would fit without swapping (as you still need extra VRAM beyond the weights, and some RAM for the system).

I did mention that it was with mmap in my comment.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment