DeepSeek-R1-GGUF is a quantized GGUF build of the DeepSeek-R1 model, so it is run through a local inference runtime such as llama.cpp or Ollama rather than a single vendor tool. Hugging Face hosts the GGUF files and documents running them locally with llama.cpp 313, Ollama runs open models locally 5, and DeepSeek publishes R1 itself 4.
- 1
Hugging Facehuggingface.coverified and signed
Hosts open models and includes a skill for selecting GGUF models to run locally with llama.cpp, covering finding GGUFs and quant selection 313.
official:MCP server · @huggingface/mcp-clientskill · huggingface-bestskill · huggingface-community-evalsskill · huggingface-gradioskill · huggingface-llm-trainer
for agents: huggingface-local-models · huggingface-llm-trainer · huggingface-community-evals
- 2
Ollamaollama.comwebsite read, tools not yet checked
Runs open AI models locally on macOS, Windows and Linux, the common way to run GGUF-format models on your own machine 5.
+136 community tools built for it
- 3
- 4
Sources
- 3Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 4DeepSeek | 深度æ±ç´¢deepseek.com · read 2026-10-30
- 5Ollama · Run AI models locally and in the cloudollama.com · read 2026-10-29
- 10Atomic Chat: Free Local AI Chat for Mac, Windows & iPhoneatomic.chat · read 2026-10-30
- 13huggingface-local-models: declares "huggingface-local-models" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14DeepSeek (Activepieces): declares "ask_deepseek" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
arize-experiment · arize-experiment verified and signed
Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluat
workers-ai-post-run-model · Cloudflare API verified and signed
Run a Workers AI model
huggingface-local-models · huggingface-local-models verified and signed
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
ask_deepseek · DeepSeek (Activepieces) verified and signed
Ask Deepseek — Ask Deepseek anything you want!
· Ollama website read, tools not yet checked
Ollama is the easiest way to run and build with open AI models locally or in the cloud on macOS, Windows, and Linux.
lucataco/deepseek-r1-70b · lucataco/deepseek-r1-70b verified and signed
DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1
hf-mem · hf-mem verified and signed
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
kcaverly/deepseek-coder-33b-instruct-gguf · kcaverly/deepseek-coder-33b-instruct-gguf verified and signed
A quantized 33B parameter language model from Deepseek for SOTA repository level code completion
llm · mistral-vibe verified and signed
deepstream-generate-pipeline · deepstream-generate-pipeline verified and signed
Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deeps
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.