Instructions to use opensota/deepseek-v4-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use opensota/deepseek-v4-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="opensota/deepseek-v4-gguf",
	filename="DeepSeek-V4-Flash-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use opensota/deepseek-v4-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf opensota/deepseek-v4-gguf:F32
# Run inference directly in the terminal:
llama-cli -hf opensota/deepseek-v4-gguf:F32

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf opensota/deepseek-v4-gguf:F32
# Run inference directly in the terminal:
llama-cli -hf opensota/deepseek-v4-gguf:F32

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 opensota/deepseek-v4-gguf:F32
# Run inference directly in the terminal:
./llama-cli -hf opensota/deepseek-v4-gguf:F32

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 opensota/deepseek-v4-gguf:F32
# Run inference directly in the terminal:
./build/bin/llama-cli -hf opensota/deepseek-v4-gguf:F32

Use Docker

docker model run hf.co/opensota/deepseek-v4-gguf:F32

LM Studio
Jan

vLLM

How to use opensota/deepseek-v4-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "opensota/deepseek-v4-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": "opensota/deepseek-v4-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/opensota/deepseek-v4-gguf:F32

Ollama
How to use opensota/deepseek-v4-gguf with Ollama:
```
ollama run hf.co/opensota/deepseek-v4-gguf:F32
```

Unsloth Studio new

How to use opensota/deepseek-v4-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 opensota/deepseek-v4-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 opensota/deepseek-v4-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for opensota/deepseek-v4-gguf to start chatting

Pi new

How to use opensota/deepseek-v4-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf opensota/deepseek-v4-gguf:F32

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": "opensota/deepseek-v4-gguf:F32"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use opensota/deepseek-v4-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 opensota/deepseek-v4-gguf:F32

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 opensota/deepseek-v4-gguf:F32

Run Hermes

hermes

Docker Model Runner
How to use opensota/deepseek-v4-gguf with Docker Model Runner:
```
docker model run hf.co/opensota/deepseek-v4-gguf:F32
```

Lemonade

How to use opensota/deepseek-v4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull opensota/deepseek-v4-gguf:F32

Run and chat with the model

lemonade run user.deepseek-v4-gguf-F32

List all available models

lemonade list

DeepSeek V4 Flash — GGUF for ds4

This quants are specific for the DS4 inference engine. They may work with other inference engines or not (they should, but not the MTP model which requires a specific loader).

https://github.com/antirez/ds4

Files

File	Size	Routed experts (`ffn_{gate,up,down}_exps`)	Everything else
`DeepSeek-V4-Flash-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2.gguf`	80.8 GiB	`IQ2_XXS` (gate, up) + `Q2_K` (down)	`Q8_0` attn proj / shared experts / output, `F16` router + embed + indexer + compressor + HC, `F32` norms / sinks / bias
`DeepSeek-V4-Flash-Q4KExperts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2.gguf`	153.3 GiB	`Q4_K` (all three)	same as above
`DeepSeek-V4-Flash-MTP-Q4K-Q8_0-F32.gguf`	3.6 GiB	MTP / speculative-decoding support (optional, not standalone).

Use q2 on 128 GB Mac machines, q4 on machines with ≥ 256 GB RAM, pair either with MTP for optional speculative decoding.

Quantization recipe

The filename is the spec. In detail, for the q2 file:

Tensor class	Quant	Notes
`blk..ffn_gate_exps`, `blk..ffn_up_exps`	`IQ2_XXS`	routed-expert up/gate
`blk.*.ffn_down_exps`	`Q2_K`	routed-expert down (K-quant for quality)
`blk.*.ffn_{gate,up,down}_shexp`	`Q8_0`	shared experts
`blk.*.attn_q_a`, `attn_q_b`, `attn_kv`, `attn_output_a`, `attn_output_b`	`Q8_0`	all attention projections (MLA + low-rank output)
`output.weight`	`Q8_0`	output head
`token_embd.weight`	`F16`	input embedding
`blk.*.ffn_gate_inp` (router)	`F16`	learned router
`blk..exp_probs_b` (router bias), `blk..attn_sinks`, all `*_norm.weight`	`F32`
`blk.*.ffn_gate_tid2eid`	`I32`	hash-routing tables (first 3 layers only)
`blk..attn_compressor_`, `blk..indexer_`, `blk..hc_`, `blk..output_hc_`	`F16` / `F32`	DSv4-specific auxiliary blocks

For the q4 file, only the three routed-expert classes change to Q4_K. Everything else is byte-for-byte identical to the q2 recipe.

The motivation behind the asymmetry: the routed experts are the majority of the parameter count but each individual expert handles only a fraction of tokens, so aggressive quantization on them costs less in average quality than the same treatment of router, projections, or shared experts. Keeping the decision-making components at Q8_0 preserves model behavior; crushing the experts buys the size.

Usage

git clone https://github.com/antirez/ds4
cd ds4
./download_model.sh q2     # 128 GB RAM machines
./download_model.sh q4     # >= 256 GB RAM machines
./download_model.sh mtp    # optional MTP / speculative decoding
make

./ds4 -p "Explain Redis streams in one paragraph."
./ds4-server --ctx 100000 --kv-disk-dir /tmp/ds4-kv --kv-disk-space-mb 8192

The download_model.sh script fetches from this repository, resumes partial downloads, and points ./ds4flash.gguf at the selected variant.

License

MIT. The base model copyright is held by DeepSeek; the GGUFs are redistributed under the base model's release terms.

Downloads last month: 480

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

16-bit

32-bit

View +2 variants

Model tree for opensota/deepseek-v4-gguf

Base model

deepseek-ai/DeepSeek-V4-Flash

Quantized

(43)

this model