Instructions to use MimiTechAI/dsv4-flash-0731-iq2xxs-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 MimiTechAI/dsv4-flash-0731-iq2xxs-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 MimiTechAI/dsv4-flash-0731-iq2xxs-gguf
# Run inference directly in the terminal:
llama cli -hf MimiTechAI/dsv4-flash-0731-iq2xxs-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MimiTechAI/dsv4-flash-0731-iq2xxs-gguf
# Run inference directly in the terminal:
llama cli -hf MimiTechAI/dsv4-flash-0731-iq2xxs-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 MimiTechAI/dsv4-flash-0731-iq2xxs-gguf
# Run inference directly in the terminal:
./llama-cli -hf MimiTechAI/dsv4-flash-0731-iq2xxs-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 MimiTechAI/dsv4-flash-0731-iq2xxs-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MimiTechAI/dsv4-flash-0731-iq2xxs-gguf

Use Docker

docker model run hf.co/MimiTechAI/dsv4-flash-0731-iq2xxs-gguf

LM Studio
Jan
Ollama
How to use MimiTechAI/dsv4-flash-0731-iq2xxs-gguf with Ollama:
```
ollama run hf.co/MimiTechAI/dsv4-flash-0731-iq2xxs-gguf
```

Unsloth Studio

How to use MimiTechAI/dsv4-flash-0731-iq2xxs-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 MimiTechAI/dsv4-flash-0731-iq2xxs-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 MimiTechAI/dsv4-flash-0731-iq2xxs-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MimiTechAI/dsv4-flash-0731-iq2xxs-gguf to start chatting

How to use MimiTechAI/dsv4-flash-0731-iq2xxs-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MimiTechAI/dsv4-flash-0731-iq2xxs-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": "MimiTechAI/dsv4-flash-0731-iq2xxs-gguf"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MimiTechAI/dsv4-flash-0731-iq2xxs-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 MimiTechAI/dsv4-flash-0731-iq2xxs-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 MimiTechAI/dsv4-flash-0731-iq2xxs-gguf

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use MimiTechAI/dsv4-flash-0731-iq2xxs-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MimiTechAI/dsv4-flash-0731-iq2xxs-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 "MimiTechAI/dsv4-flash-0731-iq2xxs-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 MimiTechAI/dsv4-flash-0731-iq2xxs-gguf with Docker Model Runner:
```
docker model run hf.co/MimiTechAI/dsv4-flash-0731-iq2xxs-gguf
```

Lemonade

How to use MimiTechAI/dsv4-flash-0731-iq2xxs-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MimiTechAI/dsv4-flash-0731-iq2xxs-gguf

Run and chat with the model

lemonade run user.dsv4-flash-0731-iq2xxs-gguf-{{QUANT_TAG}}

List all available models

lemonade list

DeepSeek-V4-Flash-0731 - IQ2XXS 2-bit GGUF

Quantized from the official deepseek-ai/DeepSeek-V4-Flash-0731 safetensors (48 shards, FP4/FP8) with the antirez/ds4 gguf-tools/deepseek4-quantize pipeline.

Recipe: IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8

Tensor family	Type
Routed experts (gate/up)	`iq2_xxs`
Routed experts (down)	`q2_K`
Attention projections	`q8_0`
Shared experts	`q8_0`
Output head	`q8_0`
Token embeddings	`f16`
Compressor / Indexer / Hyper-connections	`f16`

Size: 86.5 GB (1328 tensors)
Architecture: deepseek4, 43 layers, 256 routed experts (6 used), hash routing (3 layers), compressed KV + indexer, hyper-connections
Context: 1,048,576 tokens
Quantization: GGUF v3, imatrix: weight-energy fallback (V2 with activation imatrix planned)
tid2eid stored as I32 (ds4-engine compatible)

Usage

Runs with the ds4 engine (antirez/ds4, supports DeepSeek-V4-Flash-0731):

./ds4 -m DeepSeek-V4-Flash-0731-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8.gguf --ctx 32768

Combine with DeepSeek-V4-Flash-0731-DSpark-support.gguf (sm54) for DSpark speculative decoding:

./ds4 -m ... -mtp DeepSeek-V4-Flash-0731-DSpark-support.gguf --dspark

See the source model repo for tokenizer/config: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731

Downloads last month: 10

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MimiTechAI/dsv4-flash-0731-iq2xxs-gguf

Base model

deepseek-ai/DeepSeek-V4-Flash-0731

Quantized

(35)

this model