Instructions to use alwkala/Akhet-Ra1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alwkala/Akhet-Ra1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="alwkala/Akhet-Ra1")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("alwkala/Akhet-Ra1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use alwkala/Akhet-Ra1 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 alwkala/Akhet-Ra1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alwkala/Akhet-Ra1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf alwkala/Akhet-Ra1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alwkala/Akhet-Ra1: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 alwkala/Akhet-Ra1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf alwkala/Akhet-Ra1: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 alwkala/Akhet-Ra1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alwkala/Akhet-Ra1:Q4_K_M

Use Docker

docker model run hf.co/alwkala/Akhet-Ra1:Q4_K_M

LM Studio
Jan

vLLM

How to use alwkala/Akhet-Ra1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alwkala/Akhet-Ra1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwkala/Akhet-Ra1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alwkala/Akhet-Ra1:Q4_K_M

SGLang

How to use alwkala/Akhet-Ra1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "alwkala/Akhet-Ra1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwkala/Akhet-Ra1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "alwkala/Akhet-Ra1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwkala/Akhet-Ra1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use alwkala/Akhet-Ra1 with Ollama:
```
ollama run hf.co/alwkala/Akhet-Ra1:Q4_K_M
```
Unsloth Desktop

How to use alwkala/Akhet-Ra1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alwkala/Akhet-Ra1:Q4_K_M

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": "alwkala/Akhet-Ra1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use alwkala/Akhet-Ra1 with Docker Model Runner:
```
docker model run hf.co/alwkala/Akhet-Ra1:Q4_K_M
```

Lemonade

How to use alwkala/Akhet-Ra1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alwkala/Akhet-Ra1:Q4_K_M

Run and chat with the model

lemonade run user.Akhet-Ra1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use alwkala/Akhet-Ra1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alwkala/Akhet-Ra1:Q4_K_M

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 alwkala/Akhet-Ra1:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use alwkala/Akhet-Ra1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alwkala/Akhet-Ra1:Q4_K_M

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 "alwkala/Akhet-Ra1:Q4_K_M" \
  --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"

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Akhet-Ra1 — Model Card & Documentation

A Local-First, Arabic-Aware Language Model by Alwkala Digital Labs

Part of the AkhetRa Ecosystem (Ra: Intelligence · Akhet: Governance)

Status: Release v0.1.0 · Date: 2026-10-23
Base Model: Qwen/Qwen3.5-4B
Fine-tuned & Quantized by: Alwkala Digital Labs
Model Type: Large Language Model (LLM) · Decoder-only causal
Deployment Focus: Local inference, Private infrastructure, and Self-Hosted AI
Active Distribution: Ra-1-4B-Q4_K_M.gguf (2.52 GB)
Hugging Face Repository: alwkala/Akhet-Ra1

ملخص تنفيذي بالعربية (Executive Summary in Arabic)

«آخت-رع 1» (Akhet-Ra1) هو نموذج ذكاء اصطناعي محلي مُحسَّن بالضبط الدقيق (Fine-tuned) استناداً إلى نموذج Qwen3.5 Base، طورته Alwkala Digital Labs ليكون طبقة الذكاء (رع / Ra) داخل منظومة آخت-رع (AkhetRa). يركز النموذج على الاستدلال المحلي والسيادة على البيانات، والتعامل الذكي مع اللغتين العربية والإنجليزية، ودعم سيناريوهات الوكلاء الذكيين (Agents) والأدوات الخاضعة للحوكمة الصارمة عبر بيئة التشغيل (آخت / Akhet).

تنبيه توثيقي: هذه البطاقة تمثل المواصفات المرجعية ومعايير التقييم للنموذج. تخضع حقول الأداء والقياسات الحسابية لنتائج الاختبارات المعيارية.

1. Overview & Identity

1.1 Overview

Akhet-Ra1 serves as the primary local intelligence layer within the AkhetRa architecture:

Bringing AI capabilities directly to the edge and local hardware.
Enforcing full organizational control over infrastructure and confidential data.
Providing an integration-ready foundation for tool-calling and autonomous agents governed by the Akhet platform.

1.2 Model Identity Specification

Field	Value / Specification
Model Name	Akhet-Ra1 (GGUF Identifier: `Akhet-Ra1-4B` / Alias: `Akhet-Ra-1`)
Model Family	Akhet-Ra
Organization / Developer	Alwkala Digital Labs (alwkala.com)
Base Model	Qwen3.5 4B (`Qwen/Qwen3.5-4B`)
Model Type	Hybrid SSM + Self-Attention Causal Language Model (Qwen3.5 Architecture)
Parameter Count	4,205,751,296 (~ 4.2 Billion Parameters)
Vocabulary Size	248,320 tokens
Embedding Dimension	2,560
Hidden Layers / Blocks	32 Blocks (Hybrid SSM Mamba-style layers + Full Attention every 4 layers)
Native Trained Context	262,144 tokens (256K native training context)
Active Runtime Context	32,768 tokens (32K allocated in local server)
Reasoning Mode	Native Chain-of-Thought (`<think>...</think>` / `reasoning_content`)
Tool Calling Format	Native XML/JSON Tool Calling (`<tool_call>`, `<tool_response>`)
Base License	Apache-2.0 (`general.license: apache-2.0`)
Quantization Format	GGUF Q4_K_M (File: `Ra-1-4B-Q4_K_M.gguf`, Size: 2.52 GB)

2. Design Philosophy

Local-First: Compute resides on user hardware close to private data.
Arabic-Aware: Deep comprehension of Modern Standard Arabic, dialectal nuances (including Egyptian), technical terms, and code-switching.
Integration-Ready: Seamless coupling with runtime hooks, development tools, and agent loops.
Governance-Compatible: Designed to operate inside sandboxed runtimes enforcing strict tool access policies.
Model Agnostic Architecture: Operates independently while remaining interchangeable with external models under AkhetRa policies.

3. The AkhetRa Ecosystem Architecture

                  ┌──────────────────────────────────────────────┐
                  │                   AKHETRA                    │
                  │            The Integrated Ecosystem         │
                  └──────────────────────┬───────────────────────┘
                                         │
                 ┌───────────────────────┴───────────────────────┐
                 │                                               │
                 ▼                                               ▼
   ┌───────────────────────────┐                   ┌───────────────────────────┐
   │            RA             │                   │           AKHET           │
   │    The Intelligence Layer │                   │ The Runtime & Governance  │
   ├───────────────────────────┤                   ├───────────────────────────┤
   │ • Akhet-Ra1 LLM (Local)   │                   │ • Context & Memory Budget │
   │ • Reasoning & Generation  │◄─────────────────►│ • Tool Permissions       │
   │ • Arabic & English Logic  │  Strict Contract  │ • Sandboxing & Approvals  │
   │ • Tool Argument Synthesis │                   │ • Audit Trail & Logs      │
   └───────────────────────────┘                   └───────────────────────────┘

The Golden Principle: Ra thinks, Akhet governs.
The model produces proposals, reasoning, and tool call invocations; the Akhet runtime enforces security boundaries, schema validation, human approval, and telemetry.

4. Intended & Out-of-Scope Use Cases

4.1 Intended Use Cases (Subject to Evaluation)

Local enterprise and personal conversational assistants.
Retrieval-Augmented Generation (RAG) over private local documents.
Software development assistance, code reasoning, and debugging.
Structured data extraction, JSON formatting, and schema-compliant outputs.
Tool-assisted workflows and multi-step agent tasks.

4.2 Out-of-Scope & Prohibited Uses

Automated decision-making in medical, legal, or life-critical contexts without certified human supervision.
Autonomous execution of destructive shell or database actions without explicit runtime approval.
Bypassing base model licenses or local regulatory requirements.
Treating unverified probabilistic outputs as definitive ground truth.

5. Deployment & Quick Start

5.1 Local Execution via llama.cpp (Bundled PowerShell Scripts)

The repository includes pre-configured launch scripts optimized for NVIDIA GPUs (6GB+ VRAM):

Interactive Terminal Dashboard (TUI)

# Starts the interactive live dashboard with GPU metrics, logs, and hotkeys
.\run-Ra-tui.ps1 -Port 8080 -ContextSize 32768

Headless Service Runner

# Launches llama-server as a background/daemon service
.\run-Ra-0.ps1

Raw llama-server Command

llama-server.exe \
  -m "A:\.lmstudio\Akhet\Ra-1\Ra-1-4B-Q4_K_M.gguf" \
  --alias "Akhet-Ra-1" \
  -ngl 99 \
  -c 32768 \
  -t 8 \
  --jinja \
  --flash-attn on \
  -ctk q4_0 \
  -ctv q4_0 \
  --batch-size 1024 \
  --ubatch-size 512 \
  --host 0.0.0.0 \
  --port 8080

5.2 Direct Execution via Hugging Face Hub

Thanks to Hugging Face Hub integration and the GGUF distribution, you can run or serve Akhet-Ra1 directly without manual file downloads:

Direct CLI Execution (`llama-cli`)

# Streams inference directly using weights hosted on Hugging Face
llama-cli -hf alwkala/Akhet-Ra1:Ra-1-4B-Q4_K_M.gguf -p "أنت مساعد ذكي محلي خاضع لمنظومة آخت-رع." -cnv

Direct Server Execution (`llama-server`)

# Launches an OpenAI-compatible server on port 8080 directly from the Hub
llama-server \
  --hf-repo alwkala/Akhet-Ra1 \
  --hf-file Ra-1-4B-Q4_K_M.gguf \
  --alias "Akhet-Ra-1" \
  -c 32768 \
  -ngl 99 \
  --host 0.0.0.0 \
  --port 8080

Direct Execution via Ollama

# Pull and run directly from Hugging Face Hub via Ollama
ollama run hf.co/alwkala/Akhet-Ra1:Ra-1-4B-Q4_K_M.gguf

Custom Ollama `Modelfile`

FROM ./Ra-1-4B-Q4_K_M.gguf
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>"""
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER num_ctx 32768

5.3 Downloading the GGUF Distribution Locally

You can download Ra-1-4B-Q4_K_M.gguf (2.52 GB) for offline local deployment:

Using Hugging Face CLI (`hf`):

hf download alwkala/Akhet-Ra1 Ra-1-4B-Q4_K_M.gguf --local-dir .

Using Python (`huggingface_hub`):

from huggingface_hub import hf_hub_download

model_path = hf_hub_download(
    repo_id="alwkala/Akhet-Ra1",
    filename="Ra-1-4B-Q4_K_M.gguf",
    local_dir="."
)
print(f"Downloaded to: {model_path}")

Using LM Studio:

Open LM Studio.
Search for alwkala/Akhet-Ra1 in the model search bar.
Select Ra-1-4B-Q4_K_M.gguf and click Download.
In the System Prompt configuration, paste the system prompt from system_prompt.txt.
Load with GPU acceleration enabled (GPU Offload: Max).

5.4 Python Inference (Hugging Face Transformers / GGUF)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "alwkala/Akhet-Ra1"  # Or local path
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "system", "content": "أنت مساعد ذكي محلي خاضع لمنظومة آخت-رع."},
    {"role": "user", "content": "اشرح لي مبدأ الحوكمة الصارمة لنماذج الذكاء الاصطناعي."}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

5.5 OpenAI-Compatible Local Endpoint

Once running on http://localhost:8080, query via standard OpenAI clients:

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8080/v1", api_key="sk-no-key-required")

response = client.chat.completions.create(
    model="Akhet-Ra-1",
    messages=[
        {"role": "user", "content": "ما هي مميزات معمارية AkhetRa؟"}
    ]
)
print(response.choices[0].message.content)

6. Recommended Sampling Parameters

Parameter	Recommended Value	Description
Temperature	`0.6` – `0.7`	Balanced creativity and deterministic precision
Top-P	`0.90`	Nucleus sampling cutoff
Top-K	`40`	Limits token candidate pool
Repetition Penalty	`1.10`	Prevents cyclic repetitions in long context chains
Context Size	`32,768` (32K)	Maximum trained / tested context window
KV Cache Quantization	`q4_0` (`-ctk q4_0 -ctv q4_0`)	Halves KV cache VRAM footprint enabling 32K context on 6GB VRAM

7. Hardware & Resource Footprint

7.1 Distribution Footprint Overview

Distribution Format	File Size	Minimum VRAM / RAM	Tested Hardware	Full GPU Offload	Context Tested
GGUF Q4_K_M	2.52 GB	6 GB VRAM	NVIDIA RTX 3060 / Laptop 6GB	Yes (99 layers)	32K tokens
GGUF Q8_0	~4.3 GB (TBD)	8 GB VRAM	NVIDIA RTX 3070 / 4060 Ti	Yes	32K tokens
BF16 SafeTensors	~8.0 GB (TBD)	12 GB VRAM / 16 GB RAM	NVIDIA RTX 3060 12GB / A10G	Yes	32K tokens

7.2 VRAM & KV Cache Scaling Profile (`Ra-1-4B-Q4_K_M.gguf`)

Calculated using Hugging Face hf-mem memory estimation formulas for 4.2B parameters with Q4_K_M weights (2.52 GB):

Context Length	Weights VRAM	KV Cache (`q4_0`)	KV Cache (`f16`)	Total VRAM (`q4_0`)	Target Hardware
4,096 (4K)	2.52 GB	~0.35 GB	~0.70 GB	~2.87 GB	4GB GPUs / Integrated (Apple M-series)
8,192 (8K)	2.52 GB	~0.70 GB	~1.40 GB	~3.22 GB	4GB – 6GB GPUs
16,384 (16K)	2.52 GB	~1.40 GB	~2.80 GB	~3.92 GB	6GB VRAM GPUs
32,768 (32K)	2.52 GB	~2.80 GB	~5.60 GB	~5.32 GB	6GB VRAM GPUs (with `-ctk q4_0 -ctv q4_0`)

8. Evaluation Framework & Methodology

All benchmark claims must be validated through uniform protocols against the upstream base checkpoint (Qwen3.5 Base):

Evaluation Dimension	Benchmark / Harness	Target Metric	Base	Akhet-Ra1	Δ
Arabic Knowledge	ArabicMMLU	Accuracy (%)	[Pending]	[Pending]	[TBD]
Egyptian & Regional Dialects	Internal Egyptian Dialect Suite	Comprehension & Fluency	[Pending]	[Pending]	[TBD]
Instruction Following	IFEval	Strict Prompt Adherence	[Pending]	[Pending]	[TBD]
Reasoning & Logic	GSM8K / ARC-C	Accuracy (%)	[Pending]	[Pending]	[TBD]
Code Generation	HumanEval / MBPP	Pass@1 (%)	[Pending]	[Pending]	[TBD]
Tool Calling & Schema	BFCL / JSON-Schema Benchmark	Schema Validity Rate	[Pending]	[Pending]	[TBD]
Context Needle	RULER / Needle In A Haystack	Retrieval Accuracy	[Pending]	[Pending]	[TBD]
Safety & Jailbreak	Refusal & Prompt Injection Suite	Robustness Score	[Pending]	[Pending]	[TBD]

9. Safety, Governance & Alignment

Defense in Depth: The model's safety refusals are backed by the Akhet runtime firewall.
Untrusted Data Isolation: All web content, external RAG chunks, and tool outputs are treated as untrusted strings and never directly interpreted as system prompts.
Execution Guardrails: Any write, network, or process spawning action requires explicit user permission or pre-authorized policy tokens.

10. Citation & Attribution

@misc{alwkala_akhetra1_2026,
  title        = {Akhet-Ra1: A Local-First, Arabic-Aware Fine-Tuned Language Model},
  author       = {Alwkala Digital Labs},
  year         = {2026},
  publisher    = {Alwkala},
  howpublished = {\url{https://alwkala.com}}
}

11. Organization

Alwkala Digital Labs
Website: alwkala.com
Advancing practical AI systems, local intelligence, and governed agent frameworks across the MENA region.

Downloads last month: 19

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for alwkala/Akhet-Ra1

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(1106)

this model

You need to agree to share your Hugging Face information to access this model

Akhet-Ra1 — Model Card & Documentation

A Local-First, Arabic-Aware Language Model by Alwkala Digital Labs

Part of the AkhetRa Ecosystem (Ra: Intelligence · Akhet: Governance)

ملخص تنفيذي بالعربية (Executive Summary in Arabic)

1. Overview & Identity

1.1 Overview

1.2 Model Identity Specification

2. Design Philosophy

3. The AkhetRa Ecosystem Architecture

4. Intended & Out-of-Scope Use Cases

4.1 Intended Use Cases (Subject to Evaluation)

4.2 Out-of-Scope & Prohibited Uses

5. Deployment & Quick Start

5.1 Local Execution via llama.cpp (Bundled PowerShell Scripts)

Interactive Terminal Dashboard (TUI)

Headless Service Runner

Raw llama-server Command

5.2 Direct Execution via Hugging Face Hub

Direct CLI Execution (llama-cli)

Direct Server Execution (llama-server)

Direct Execution via Ollama

Custom Ollama Modelfile

5.3 Downloading the GGUF Distribution Locally

Using Hugging Face CLI (hf):

Using Python (huggingface_hub):

Using LM Studio:

5.4 Python Inference (Hugging Face Transformers / GGUF)

5.5 OpenAI-Compatible Local Endpoint

6. Recommended Sampling Parameters

7. Hardware & Resource Footprint

7.1 Distribution Footprint Overview

7.2 VRAM & KV Cache Scaling Profile (Ra-1-4B-Q4_K_M.gguf)

8. Evaluation Framework & Methodology

9. Safety, Governance & Alignment

10. Citation & Attribution

11. Organization

Model tree for alwkala/Akhet-Ra1

Direct CLI Execution (`llama-cli`)

Direct Server Execution (`llama-server`)

Custom Ollama `Modelfile`

Using Hugging Face CLI (`hf`):

Using Python (`huggingface_hub`):

7.2 VRAM & KV Cache Scaling Profile (`Ra-1-4B-Q4_K_M.gguf`)