Instructions to use dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-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 dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-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 dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

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 dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

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 dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

Use Docker

docker model run hf.co/dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF with Ollama:
```
ollama run hf.co/dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0
```
Unsloth Desktop

How to use dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

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": "dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF with Docker Model Runner:
```
docker model run hf.co/dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0
```

Lemonade

How to use dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-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 dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

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 dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0

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 "dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF:Q8_0" \
  --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 Flash 0731 compact DSpark drafters

This repository contains the compact DSpark auxiliary for DeepSeek V4 Flash 0731. It is not a standalone language model and does not include target-model weights.

Artifact

File	Bytes	SHA-256
`DeepSeek-V4-Flash-0731-DSpark-Drafter-Q2_K-Q8_0-dflash.gguf`	6,976,490,112	`2c8065906a7b4d841e10f15b350ed14410fe715df3973e9622dccd278ed28e8e`
`DeepSeek-V4-Flash-0731-DSpark-Drafter-IQ2_XXS-MXFP4-Q8_0-dflash.gguf`	7,302,985,888	`e4b2b63356e11823c81eb2d3dc9739ae3c2935b970747c9b3be101548a3c17ec`

The routed experts use Q2_K. Dense projections use Q8_0. The 81-tensor GGUF uses the standardized llama.cpp general.architecture=dflash schema.

The Q2_K artifact is the smallest option. The mixed artifact uses IQ2_XXS for the gate and up routed-expert tensors and preserves the down routed-expert tensors in native MXFP4. Its remaining quantized tensors use Q8_0. The mixed recipe follows the small-drafter design from antirez/ds4 issue 642 and keeps more expert fidelity while remaining suitable for 128 GiB Apple Silicon Macs. The target, drafter, KV cache, runtime buffers, and other loaded models must still fit together.

Unsloth publishes a full-MXFP4 Q8_0 drafter and a BF16 drafter. This repository provides the smaller mixed expert recipe that Unsloth does not publish.

Download

hf download dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF \
  DeepSeek-V4-Flash-0731-DSpark-Drafter-IQ2_XXS-MXFP4-Q8_0-dflash.gguf

Provenance and verification

The source is deepseek-ai/DeepSeek-V4-Flash-0731 revision 9e165c30e2704aec5d9d593cce3eebd58bbef1cb. The repository contains the pinned source manifest, the Q2_K converter, standardized dflash rewriters, verification scripts, tests, build manifests, and checksums.

Both releases passed these schema checks:

81 canonical dflash tensors with 32-byte alignment.
Byte-identical tensor payloads before and after the schema rewrite.
Byte-identical repeated builds.
Complete target-tokenizer metadata copied through the official llama.cpp DeepSeek V4 DSpark converter at commit 15586e2d7165570fb3aa7c26e0d442e289ef69de, including tokenizer.ggml.mask_token_id=128799.
A real llama.cpp draft-dspark decode generated 120 draft tokens and accepted 38, with no invalid -1 token.
ns4 build e470f38280d9ff4f020c242233998562a88463ee loaded the corrected Q2 file and completed an exact 32-token decode, drafting 47 and accepting 12.

The Q2_K build also passed its numeric limits: maximum Q2_K block-relative error 0.49072265625, below 0.5, and maximum Q8_0 block-relative error 0.00396728515625, below 0.01.

The mixed artifact was converted with antirez/ds4 pull request 645 at commit d147270d7422ba0eb55985c8d4075b9dfaa84bf1. It uses the public routed-MoE importance matrix from antirez/deepseek-v4-gguf. The build manifest pins its revision, checksum, and the deterministic MTP alias transformation.

Reproduce the artifact on Linux AArch64 with Python 3.14:

uv venv --python 3.14.6 .venv
uv pip install --python .venv/bin/python \
  --require-hashes --only-binary=:all: \
  -r requirements-linux-aarch64-py314.lock
.venv/bin/python scripts/download_sources.py --destination sources
.venv/bin/python -m unittest discover -s tests -v
.venv/bin/python scripts/reproduce.py \
  --sources sources --recipe q2_k-q8_0 \
  --manifest-dir manifest --repeat-check
.venv/bin/python scripts/dflash.py \
  --sources sources --recipe q2_k-q8_0 \
  --legacy-input DeepSeek-V4-Flash-0731-DSpark-Drafter-Q2_K-Q8_0.gguf \
  --target-tokenizer-gguf tokenizer.gguf \
  --manifest-dir manifest --repeat-check

# The mixed legacy GGUF is produced with the pinned ds4 converter and imatrix.
.venv/bin/python scripts/rewrite_mixed_dflash.py \
  DeepSeek-V4-Flash-0731-DSpark-Drafter-IQ2_XXS-MXFP4-Q8_0.gguf \
  --target-tokenizer-gguf tokenizer.gguf \
  --manifest-dir manifest

Compatibility

Use this file only with a compatible DeepSeek V4 Flash 0731 target. The runtime must support the standardized llama.cpp dflash GGUF schema and the selected Q2_K or IQ2_XXS/MXFP4 expert recipe. This is a community conversion, not an official DeepSeek release.

The source-derived weights remain under DeepSeek's MIT license. Conversion code and third-party notices are provided in LICENSE.code and THIRD_PARTY_NOTICES.md.

Downloads last month: 745

GGUF

Model size

20B params

Architecture

dflash

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF

Base model

deepseek-ai/DeepSeek-V4-Flash-0731

Quantized

(193)

this model