Instructions to use thetom-ai/DeepSeek-V4-Flash-ConfigI-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 thetom-ai/DeepSeek-V4-Flash-ConfigI-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 thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF
# Run inference directly in the terminal:
llama cli -hf thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF
# Run inference directly in the terminal:
llama cli -hf thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

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 thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF
# Run inference directly in the terminal:
./llama-cli -hf thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

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 thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

Use Docker

docker model run hf.co/thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

LM Studio
Jan

vLLM

How to use thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

Ollama
How to use thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF with Ollama:
```
ollama run hf.co/thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF
```

Unsloth Studio

How to use thetom-ai/DeepSeek-V4-Flash-ConfigI-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 thetom-ai/DeepSeek-V4-Flash-ConfigI-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 thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

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": "thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use thetom-ai/DeepSeek-V4-Flash-ConfigI-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 thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

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 thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

Run Hermes

hermes

OpenClaw new

How to use thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

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 "thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF" \
  --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"

Docker Model Runner
How to use thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF with Docker Model Runner:
```
docker model run hf.co/thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF
```

Lemonade

How to use thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-ConfigI-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

DeepSeek-V4-Flash — Config-I (GGUF)

284B-parameter MoE (21B active) in 95 GiB — fits and runs on 128 GB unified-memory boxes (DGX Spark, Mac). Config-I hybrid quantization at 2.88 bpw effective.

Config-I quantization of deepseek-ai/DeepSeek-V4-Flash-0731 — the official 2026-07-31 release, superseding the preview — (43 layers, 256 routed experts top-6, hash routing, MLA attention, mHC hyper-connections, DSA indexer). Sibling release: Config-I MLX for Apple Silicon.

📖 How to actually run it well: the offlabel operating guide covers the backend traps, sampling, the repetition-loop fix, and the DwarfStar speed comparison in one place.

⚠️ Runtime requirement

This GGUF uses the TurboQuant TQ3_1S weight type, so it needs the TurboQuant llama.cpp fork rather than stock llama.cpp:

git clone https://github.com/TheTom/llama-cpp-turboquant
cd llama-cpp-turboquant          # default branch is what you want
cmake -B build -DGGML_CUDA=ON    # or -DGGML_METAL=ON on a Mac
cmake --build build -j

Verified against the fork's default branch (feature/turboquant-kv-cache): loads and generates correctly on both Metal and CUDA.

Recipe

Tensor group	Type	bpw
Expert gate/up (all layers)	Q2_0	2.25
Expert down, attention, indexer, compressor	TQ3_1S (WHT-rotated)	4.0
Token embeddings	q8_0	8.5
Output head	q6_K	6.6
Router gates, mHC mixing, APE, norms, sinks	f32/bf16	—

Compression

	Size
FP8/FP4 source	167 GB
BF16 equivalent	~570 GB
Config-I hybrid (2.88 bpw)	95 GiB (102 GB), 3 split files ≤45 GB

Quality

Wikitext PPL: 15.64 ± 0.38 (ctx 512, 60 chunks) · 12.86 ± 0.29 (ctx 2048, 15 chunks) — measured on CUDA (GB10)
Coherent greedy generation verified on CUDA, CPU, and Metal.

Observed behaviors at 2.88 bpw (honesty notes, measured under heavy I/O contention — quiet-condition re-runs pending):

Use the official sampling settings: temperature 1.0, top_p 0.95 (DeepSeek's card). Greedy decoding (temp 0) induces repetition loops on this model family and is not representative.
The post-</think> content stream can degenerate into repetition while the correct answer sits intact in the reasoning block — parse reasoning_content when serving with reasoning enabled (observed under greedy decoding; official sampling mitigates).
Repetition on hard symbolic math was observed under greedy decoding only — being re-evaluated at official sampling settings.
Broader MMLU/NIAH numbers land here after quiet-condition runs complete.

Example

TQ_NO_ROTATE=1 ./build/bin/llama-cli -m DeepSeek-V4-Flash-0731-ConfigI-00001-of-00003.gguf \
  -ngl 99 -c 8192 --temp 1.0 --top-p 0.95 -p "your prompt" -st < /dev/null

License

Inherits the DeepSeek model license from the base model. Quantization by thetom-ai.

Downloads last month: 753

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF

Base model

deepseek-ai/DeepSeek-V4-Flash-0731

Quantized

(78)

this model