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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="batiai/DeepSeek-V4-Flash-GGUF",
	filename="deepseek-ai-DeepSeek-V4-Flash-Q3_K_M-00001-of-00003.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use batiai/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 batiai/DeepSeek-V4-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf batiai/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 batiai/DeepSeek-V4-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf batiai/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 batiai/DeepSeek-V4-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf batiai/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 batiai/DeepSeek-V4-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf batiai/DeepSeek-V4-Flash-GGUF:Q4_K_M

Use Docker

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

LM Studio
Jan

vLLM

How to use batiai/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 "batiai/DeepSeek-V4-Flash-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "batiai/DeepSeek-V4-Flash-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

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

Unsloth Studio

How to use batiai/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 batiai/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 batiai/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 batiai/DeepSeek-V4-Flash-GGUF to start chatting

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

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull batiai/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

DeepSeek V4-Flash GGUF — BatiAI Early Access

⚠️ Early Access — requires bati.cpp to run. DeepSeek V4-Flash was released on 2026-04-24 and is not yet supported by ggml-org/llama.cpp master. This GGUF was converted with batiai/bati.cpp — BatiAI's own inference library — and inference also requires the same library. Ollama is not yet compatible (will auto-update once mainline merges V4 support).

Why ship now?

V4-Flash is a frontier-class model (284B-A13B, top-tier on SWE-Bench Pro). Mainline support will likely take 1-2 more weeks. We provide this interim release so power users can evaluate the model immediately. When mainline merges support, this repo will gain imatrix-calibrated IQ3_XXS / IQ4_XS / Q5_K_M plus Ollama push.

Available Quants

Quant	Size	Recommended hardware	Notes
Q3_K_M	127 GB	128 GB unified memory (M4 Max)	3-bit, smallest
Q4_K_M	161 GB	192 GB+ Mac	balanced — recommended
Q5_K_M	188 GB	256 GB+ Mac	higher fidelity
Q6_K	218 GB	384 GB+ Mac	near-lossless
Q8_0	282 GB	M3 Ultra 512 GB	original FP4 → Q8_0 dequant

All quants signed by BatiAI (general.author=BatiAI, general.url=https://flow.bati.ai).

Note: IQ-quants (IQ3_XXS / IQ4_XS) are tracked in bati.cpp v0.2.0. They require imatrix calibration, and llama-imatrix currently segfaults during V4-Flash model context init in the fork. Will be added once that path is fixed (or once mainline llama.cpp merges V4 support). K-quants above use bati.cpp v0.1.2's integer-tensor pass-through patch.

How to run inference (build `bati.cpp`)

# 1. Clone + build BatiAI's inference library
git clone https://github.com/batiai/bati.cpp.git
cd bati.cpp
cmake -B build -DGGML_CUDA=ON      # Linux
# or: cmake -B build -DGGML_METAL=ON  # macOS (Mac Studio M3 Ultra 512GB recommended)
cmake --build build -j 16 --target llama-cli llama-gguf-split

# 2. Download shards + merge into a single GGUF
hf download batiai/DeepSeek-V4-Flash-GGUF --local-dir ./v4-flash
build/bin/llama-gguf-split --merge \
    ./v4-flash/deepseek-ai-DeepSeek-V4-Flash-Q8_0-00001-of-00007.gguf \
    ./v4-flash/merged-Q8_0.gguf

# 3. Inference
build/bin/llama-cli -m ./v4-flash/merged-Q8_0.gguf -cnv -ngl 99 -c 4096

Model details

Source: deepseek-ai/DeepSeek-V4-Flash
Architecture: 284B total / 13B active MoE, 1M context window
Hybrid attention: Compressed Sparse Attention (CSA) + Heavily Compressed Attention (HCA)
Original precision: FP4 + FP8 mixed (FP4 expert weights, FP8 attention)
This GGUF: Q8_0 dequantization (FP4 → Q8_0 directly; BF16 intermediate skipped)
License: MIT

What happens after mainline merges V4

When ggml-org/llama.cpp master merges DeepSeek V4:

We rebuild with mainline + run imatrix calibration (wikitext-2, 200 chunks)
Add IQ3_XXS, IQ4_XS, Q5_K_M quants to this repo (BatiAI-signed)
Push to Ollama: batiai/deepseek-v4-flash:iq3 / :iq4 / :q5
Run real-hardware Mac benchmarks (M3 Ultra 512GB)
bati.cpp's V4 support transitions to read-only archive (users migrate to mainline)

Watch this repo for the update.

BatiAI signing

All GGUFs in this repo carry:

general.author = BatiAI
general.url = https://flow.bati.ai

About `bati.cpp`

batiai/bati.cpp is BatiAI's own inference library — a llama.cpp-based fork focused on Apple Silicon, frontier-model early access, and BatiAI's quantization standard. Built on top of ggml-org/llama.cpp and antirez/llama.cpp-deepseek-v4-flash (all MIT). See bati.cpp's ATTRIBUTION.md for full credits.

License

Inherits the source model license: MIT.

About BatiFlow

BatiFlow — free on-device AI automation for Mac.

Downloads last month: 2,963

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for batiai/DeepSeek-V4-Flash-GGUF

Base model

deepseek-ai/DeepSeek-V4-Flash

Quantized

(68)

this model

Collection including batiai/DeepSeek-V4-Flash-GGUF

🚀 Frontier MoE — 128B–1T

Collection

Largest open-weight LLMs, BatiAI-quantized. Mac-runnable from M4 Max 128GB to Mac Studio M3 Ultra 512GB. • 7 items • Updated 27 days ago