Instructions to use YourHighnessLA/L0xRE-27b-Low with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use YourHighnessLA/L0xRE-27b-Low 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 YourHighnessLA/L0xRE-27b-Low:Q2_K
# Run inference directly in the terminal:
llama cli -hf YourHighnessLA/L0xRE-27b-Low:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf YourHighnessLA/L0xRE-27b-Low:Q2_K
# Run inference directly in the terminal:
llama cli -hf YourHighnessLA/L0xRE-27b-Low:Q2_K

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 YourHighnessLA/L0xRE-27b-Low:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf YourHighnessLA/L0xRE-27b-Low:Q2_K

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 YourHighnessLA/L0xRE-27b-Low:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf YourHighnessLA/L0xRE-27b-Low:Q2_K

Use Docker

docker model run hf.co/YourHighnessLA/L0xRE-27b-Low:Q2_K

Llama new
LM Studio
Jan

vLLM

How to use YourHighnessLA/L0xRE-27b-Low with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YourHighnessLA/L0xRE-27b-Low"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YourHighnessLA/L0xRE-27b-Low",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YourHighnessLA/L0xRE-27b-Low:Q2_K

Ollama
How to use YourHighnessLA/L0xRE-27b-Low with Ollama:
```
ollama run hf.co/YourHighnessLA/L0xRE-27b-Low:Q2_K
```
Unsloth Desktop

How to use YourHighnessLA/L0xRE-27b-Low with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YourHighnessLA/L0xRE-27b-Low:Q2_K

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": "YourHighnessLA/L0xRE-27b-Low:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use YourHighnessLA/L0xRE-27b-Low with Docker Model Runner:
```
docker model run hf.co/YourHighnessLA/L0xRE-27b-Low:Q2_K
```

Lemonade

How to use YourHighnessLA/L0xRE-27b-Low with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YourHighnessLA/L0xRE-27b-Low:Q2_K

Run and chat with the model

lemonade run user.L0xRE-27b-Low-Q2_K

List all available models

lemonade list

Hermes Agent

How to use YourHighnessLA/L0xRE-27b-Low with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YourHighnessLA/L0xRE-27b-Low:Q2_K

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 YourHighnessLA/L0xRE-27b-Low:Q2_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use YourHighnessLA/L0xRE-27b-Low with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YourHighnessLA/L0xRE-27b-Low:Q2_K

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 "YourHighnessLA/L0xRE-27b-Low:Q2_K" \
  --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"

L0xRE-27b-Low

A 27-billion-parameter model built for a small GPU-memory footprint — 8.62 GB on disk, running on any RTX 30/40/50 card with at least 12 GB of VRAM. Paired with the L0xRE BeeLLama Low runtime, it serves as a fast, smart, small agentic coding assistant on your own machine.

“27b” is the parameter count, not the download size. “Low” describes the memory-focused model build. Context length depends on the card, runtime profile, and other applications.

Start here: the runtime README — one installer command per OS. The official release with every package, checksum, and certification receipt is beellama-v0.4.7-r6.

Download these two files

File	What it does	Download size
L0xRE-27b-Low.gguf	The main model. This is the recommended model file.	8.62 GB
Qwen3.8-27B-DFlash2-Q4_K_M.gguf	Recommended drafter: the runtime uses it to propose tokens that the main model verifies (DFlash2 speculative decoding).	1.14 GB

For the recommended setup, download both files: 9.76 GB in total, plus the runtime package. The installer fetches and verifies both automatically. The main model can also run without a drafter, with speculative decoding disabled.

The smaller Qwen3.8-27B-DFlash2-Q2_K.gguf file is an optional 705 MB drafter for memory-constrained experiments. Start with the recommended Q4_K_M drafter to match the published certified configurations.

Install and run

The guided installer detects your GPU, picks the right certified or starter package, verifies every SHA-256, downloads these files, and prints a ready-to-run start command:

# Linux / WSL — see the runtime README for the fetch command
bash install-l0xre.sh

# Windows
powershell -NoProfile -ExecutionPolicy Bypass -File .\install-l0xre.ps1

When ready, the server's health endpoint is http://127.0.0.1:8080/health and its API base is http://127.0.0.1:8080/v1. For a compatible chat client or coding agent, use that API base and select L0xRE-27b-Low from the server's /v1/models endpoint.

This model requires the L0xRE BeeLLama Low runtime. Direct use with stock llama.cpp, Ollama, LM Studio, Transformers, or other inference engines is outside this release's supported setup. The GGUF extension alone does not establish compatibility.

GPU support and context

GPU / OS	Certified configuration	Status
RTX 30 series ≥12 GB / Linux	80K context, KVarN4/4 KV, DFlash2 N7 — measured on RTX 3060	Certified
RTX 40 series ≥12 GB / Linux	80K context — certified on RTX 4090; starter profile on other cards	Certified (4090) / Starter
RTX 5090 32 GB / Linux or Windows	80K context, CUDA 13.0 on Windows	Certified
Other RTX 50 series ≥12 GB	32K starter profile	Starter
RTX 30/40 series / Windows	80K profile; RTX 4070 Ti measured 68/116 t/s	Starter

Certified routes passed correctness, capacity, soak, and consumer-probe gates on the exact card. Starter routes ship the best measured configuration so far, clearly labeled. See the architecture status for details.

Measured speed (frozen Bench.sh protocol)

Hardware	Prose	Code	Cold prefill
RTX 3060 12 GB, Linux	37 t/s	65 t/s	566 t/s (10K)
RTX 4090 24 GB, Linux	104 t/s	167 t/s	2,034 t/s (10K)
RTX 5090 32 GB, Linux	131 t/s	229 t/s	3,527 t/s
RTX 5090 32 GB, Windows	137 t/s	230 t/s	3,611 t/s
RTX 4070 Ti 12 GB, Windows (starter)	68 t/s	116 t/s	—

These are workload-specific certified measurements with published receipts, not guaranteed speeds for every prompt. Quality scores from other checkpoints in the model family are not presented as an evaluation of this exact file. No external leaderboard result is claimed here.

File integrity

Download sizes use decimal GB.

File	Bytes	SHA-256
`L0xRE-27b-Low.gguf`	8,619,127,680	`b0849250c633aa93853bf119a877dbdafdd7b1a4ebb672bd6b6a1439906f3543`
`Qwen3.8-27B-DFlash2-Q4_K_M.gguf`	1,143,006,816	`1a25c56858e1ebe93f2718ac1d49d1151f9323325c1bbfd6209370f4db131ebd`
`Qwen3.8-27B-DFlash2-Q2_K.gguf`	705,430,880	`e3eb7705404817cdbcdabe56049a1952b3b37bcc8df6e4d4efaec5d41563fb7e`

Related checkpoint

L0xRE-27b-Low-MTP is a separate, larger checkpoint with an additional prediction block. Its file hash, runtime setup and qualification are distinct. Use the main model file on this page for the recommended drafter-based setup.

Model origin and license

L0xRE-27b-Low is a quantized derivative of Qwen3.8-27B, with low-bit projections and higher-precision embeddings/output tensors. The model's configured native context capacity is 262,144 tokens; supported and tested serving contexts are determined by the runtime profiles above.

Model weights remain under the base model's research/community terms: license. The L0xRE runtime tooling ships under the BeeLlama license with third-party notices in its packages. Model licensing and runtime licensing are separate.

Downloads last month: 721

GGUF

Model size

5B params

Architecture

escha

Hardware compatibility

2-bit

4-bit

View +1 variant

Model tree for YourHighnessLA/L0xRE-27b-Low

Base model

Qwen/Qwen3.8-27B

Quantized

(1598)

this model