Instructions to use 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS 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 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S
# Run inference directly in the terminal:
llama cli -hf 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S
# Run inference directly in the terminal:
llama cli -hf 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

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 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S
# Run inference directly in the terminal:
./llama-cli -hf 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

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 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

Use Docker

docker model run hf.co/0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

LM Studio
Jan
Ollama
How to use 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS with Ollama:
```
ollama run hf.co/0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S
```

Unsloth Studio

How to use 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS 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 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS 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 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS to start chatting

How to use 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

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 "0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S" \
  --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"

Docker Model Runner
How to use 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS with Docker Model Runner:
```
docker model run hf.co/0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S
```

Lemonade

How to use 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

Run and chat with the model

lemonade run user.Kimi-K3-IQ1S-REAP568-64K-4XSPARKS-UD-IQ1_S

List all available models

lemonade list

Hermes Agent

How to use 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

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 0xTank/Kimi-K3-IQ1S-REAP568-64K-4XSPARKS:UD-IQ1_S

Run Hermes

hermes

Atomic Chat

Kimi-K3-IQ1S-REAP568-64K-4XSPARKS / recipes /launch_4x_spark_600k_f16k.sh

0xTank

Record FP16-K prefill A/B candidate

5bfcd16 verified 5 days ago

Raw

History Blame Contribute Delete

865 Bytes

	#!/usr/bin/env bash
	# Candidate-only FP16-K prefill variant measured on 2026-08-01.
	set -euo pipefail
	BIN_DIR=${BIN_DIR:-/opt/llama.cpp-kimi-k3-candidate/build-flashkda-iq1s-v1/bin}
	MODEL=${MODEL:-$PWD/Kimi-K3-UD-IQ1_S-00001-of-00014.gguf}
	RPC_WORKERS=${RPC_WORKERS:-10.10.10.1:50053,10.10.10.2:50053,10.10.10.4:50053}
	PORT=${PORT:-8210}
	exec env GGML_RPC_SKIP_HASH=1 CUDA_SCALE_LAUNCH_QUEUES=4x LLAMA_MMAP_PREFETCH=0 LLAMA_PARALLEL_DEVICE_LOAD=1 "$BIN_DIR/llama-server" \
	--model "$MODEL" --alias kimi-k3-f16k-600k-u1024 \
	--host 0.0.0.0 --port "$PORT" --ctx-size 600000 --parallel 1 \
	--n-gpu-layers 999 --rpc "$RPC_WORKERS" --split-mode layer --tensor-split 1,1,1,1 \
	--flash-attn on --fit off --cache-type-k f16 --cache-type-v f16 \
	--batch-size 2048 --ubatch-size 1024 --threads 16 --threads-batch 20 \
	--cache-reuse 256 --reasoning auto --metrics