Instructions to use cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-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 cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF # Run inference directly in the terminal: llama cli -hf cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF # Run inference directly in the terminal: llama cli -hf cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF # Run inference directly in the terminal: ./build/bin/llama cli -hf cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
Use Docker
docker model run hf.co/cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
- Llama new
- LM Studio
- Jan
- vLLM
How to use cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-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": "cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
- Ollama
How to use cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF with Ollama:
ollama run hf.co/cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
- Unsloth Desktop
- Pi
How to use cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF with Docker Model Runner:
docker model run hf.co/cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
- Lemonade
How to use cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
Run and chat with the model
lemonade run user.DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-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 cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-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://127.0.0.1:9931/v1 hermes config set model.default cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-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://127.0.0.1:9931/v1 \ --custom-model-id "cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-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"
Download llama-quant-dither-zeros.patch from cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 2.28 kB
-
https://huggingface.co/cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF/resolve/main/llama-quant-dither-zeros.patch
- Command line
-
hf download hf://cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF/llama-quant-dither-zeros.patch
-
curl -L -o llama-quant-dither-zeros.patch https://huggingface.co/cliecy/DeepSeek-V4.1-Flash-1017-UD-IQ2XS-GGUF/resolve/main/llama-quant-dither-zeros.patch
2.28 kB
| --- a/src/llama-quant.cpp | |
| +++ b/src/llama-quant.cpp | |
| f32_data = (const float *) f32_conv_buf.data(); | |
| } | |
| + // LLAMA_QUANT_DITHER_ZEROS=1: the IQ2 grids have no zero level, and the IQ2 quantizers give | |
| + // x == 0 a positive sign. A source with many exact zeros (MXFP4 experts: ~12 %) then gets the | |
| + // same positive error at every zero, which adds up along each row (measured for IQ2_XS and | |
| + // IQ2_S). A tiny pseudo-random sign on the zeros turns that into unbiased noise. IQ3_XXS/IQ3_S | |
| + // also lack a zero level and are included, but were not measured. | |
| + static const bool dither_zeros = getenv("LLAMA_QUANT_DITHER_ZEROS") && atoi(getenv("LLAMA_QUANT_DITHER_ZEROS")); | |
| + if (dither_zeros && ( | |
| + new_type == GGML_TYPE_IQ2_XXS || new_type == GGML_TYPE_IQ2_XS || new_type == GGML_TYPE_IQ2_S || | |
| + new_type == GGML_TYPE_IQ3_XXS || new_type == GGML_TYPE_IQ3_S)) { | |
| + if (f32_data != (const float *) f32_conv_buf.data()) { | |
| + if (f32_conv_buf.size() < (size_t) nelements_cur) { | |
| + f32_conv_buf.resize(nelements_cur); | |
| + } | |
| + memcpy(f32_conv_buf.data(), f32_data, nelements_cur*sizeof(float)); | |
| + f32_data = (const float *) f32_conv_buf.data(); | |
| + } | |
| + float * x = (float *) f32_conv_buf.data(); | |
| + const uint64_t base = (uint64_t) ir * n_per_row; | |
| + for (int64_t j = 0; j < nelements_cur; ++j) { | |
| + if (x[j] == 0.0f) { | |
| + uint64_t h = (base + j + 1) * 0x9E3779B97F4A7C15ULL; | |
| + h ^= h >> 31; | |
| + x[j] = (h & 1) ? 1e-20f : -1e-20f; | |
| + } | |
| + } | |
| + } | |
| + | |
| if (work.size() < nrows_cur*row_size_dst) { | |
| work.resize(nrows_cur*row_size_dst); | |
| } | |