Instructions to use peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-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 peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-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 peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS
# Run inference directly in the terminal:
llama cli -hf peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS
# Run inference directly in the terminal:
llama cli -hf peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

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 peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS
# Run inference directly in the terminal:
./llama-cli -hf peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

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 peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

Use Docker

docker model run hf.co/peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

Llama new
LM Studio
Jan

vLLM

How to use peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-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": "peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

Ollama
How to use peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF with Ollama:
```
ollama run hf.co/peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS
```
Unsloth Desktop

How to use peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

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": "peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF with Docker Model Runner:
```
docker model run hf.co/peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS
```

Lemonade

How to use peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

Run and chat with the model

lemonade run user.DeepSeek-V4.1-Flash-1017-Maya-GGUF-IQ2_XXS

List all available models

lemonade list

Hermes Agent

How to use peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-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 peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

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 peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS

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 "peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF:IQ2_XXS" \
  --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-V4.1-Flash-1017 · Maya GGUF

GGUF quantizations of deepseek-ai/DeepSeek-V4.1-Flash-1017 (a mixture of experts: 384 routed experts per layer, 6 active per token, plus a shared expert), made for Project Maya. Project Maya keeps the most-used experts on the GPU and reads the rest from RAM and the SSD, so the model runs well below its size. Both quants are made from DeepSeek's own release (FP4 experts, FP8 dense weights), not from a re-quantized file, and keep every expert.

Two quants

	Maya-S	Maya-XS
Made for	the closest answers to the original	the whole model in a 128 GB PC's memory
Model in memory	178.2 GB	115.3 GB
DSpark drafter	8.0 GB (DeepSeek's FP4 experts)	4.3 GB (its own, 2-bit experts)
Engram tables (read from the SSD)	161.3 GB	161.3 GB
Download, all files	347.5 GB	280.9 GB
Routed experts	IQ2_XXS gate/up, IQ3_XXS down (IQ2_S / IQ3_S in the first and last four layers)	IQ1_S
Attention, shared experts, embeddings, output	Q8_0	Q8_0
Same top token as the original	92.6%	87.5%
Next-token loss (NLL) vs the original	+3.2%	+8.7%

Measured on held-out text never used for calibration, against the original model's own predictions (DeepSeek's reference implementation running the original weights). As a yardstick, the original weights run through Project Maya's engine give 96.4% - the engine's own rounding; the rest of each quant's distance is the quantization.

Built partly on the IST Austria DAS Lab (ISTA-DASLab) recipe. The experts are rounded with GPTQ-style error feedback (each against its own input statistics), and the result is measured against the full-precision model.

How they were made

Calibration text in DeepSeek's own chat format, thinking included: code, tool calls and agent traces, reasoning, chat, multilingual. Maya-S: 128 sequences of 2,048 tokens; Maya-XS: three times as many, plus the model's own answers. A separate held-out set is kept for evaluation.
Statistics from the model itself, layer by layer, an importance matrix for every expert separately. Maya-XS is calibrated on the quantized model itself: each layer sees what the already-quantized layers before it produce.
Error-feedback rounding of every expert, at the quantizer's 256-weight blocks, each expert against its own input statistics.
The Engram tables (DeepSeek's n-gram memory) in Q6_K: against the tables as released (FP8) they cost no measurable quality (97.5% the same top token - the measurement's own noise floor). They are read a few rows a token from the SSD, so they cost disk space, not memory.
llama.cpp's own quantizers (ggml), so the files are ordinary GGUFs.

Files

Folder	Files	Size
`Maya-S/`	`DeepSeek-V4.1-Flash-1017-Maya-S-IQ2_XXS-00001-of-00006.gguf` … `-00006-of-00006.gguf`: the model in files 1-4, the Engram tables in files 5-6	339.5 GB
`Maya-XS/`	`DeepSeek-V4.1-Flash-1017-Maya-XS-IQ1_S-00001-of-00005.gguf` … `-00005-of-00005.gguf`: the model in files 1-3, the Engram tables in files 4-5	276.6 GB
`dspark/`	`dspark.bin` / `.json`: Maya-S's drafter; `dspark-xs2.bin` / `.json`: Maya-XS's drafter	8.0 / 4.3 GB

Router, norms, hyper-connection mixing and attention sinks stay as released (F32 / BF16). The vision tower comes from DeepSeek's own checkpoint, unchanged; the setup fetches it.

Running it

Project Maya sets everything up and runs it:

git clone https://github.com/mw00/project-maya.git && cd project-maya
./setup.sh --setup --model DeepSeek-V4.1-Flash-1017 --ds4-quant maya-s     # Windows: START-MAYA.bat
./setup.sh --setup --model DeepSeek-V4.1-Flash-1017 --ds4-quant maya-xs    # v1.1.22 or later

It checks the PC, downloads the files (every one verified by its sha256, resumed if a download stops), compiles the engine for your GPU(s) and starts it: the dashboard at http://127.0.0.1:8080, or the OpenAI- and Anthropic-compatible API at the same address (streaming, tool calls, pictures).

License

The model is DeepSeek's DeepSeek-V4.1-Flash-1017 under the MIT license; these quantizations are released under the same license.

Downloads last month: 121,672

GGUF

Model size

748B params

Architecture

deepseek41

Hardware compatibility

1-bit

2-bit

Model tree for peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF

Base model

deepseek-ai/DeepSeek-V4.1-Flash-1017

Quantized

(151)

this model

Quantizations

3 models