Instructions to use kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-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 kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-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 kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-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 kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-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 kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M

Use Docker

docker model run hf.co/kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF with Ollama:
```
ollama run hf.co/kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF with Docker Model Runner:
```
docker model run hf.co/kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M
```

Lemonade

How to use kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kirikir13/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

DeepSeek-R1-0528-Qwen3-8B heretic — GGUF Q4_K_M

Converted with llama.cpp (convert_hf_to_gguf.py → F16 → llama-quantize Q4_K_M, 4.90 BPW). Reasoning model: emits <think>…</think>. Note: the tokenizer pre-tokenizer hash was unknown to llama.cpp; it uses the Qwen2 regex, so it was mapped to qwen2.

Downloads last month: -

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

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