Instructions to use openamer-max/openamer-max-desktop with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use openamer-max/openamer-max-desktop 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 openamer-max/openamer-max-desktop
# Run inference directly in the terminal:
llama cli -hf openamer-max/openamer-max-desktop

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf openamer-max/openamer-max-desktop
# Run inference directly in the terminal:
llama cli -hf openamer-max/openamer-max-desktop

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf openamer-max/openamer-max-desktop
# Run inference directly in the terminal:
./build/bin/llama cli -hf openamer-max/openamer-max-desktop

Use Docker

docker model run hf.co/openamer-max/openamer-max-desktop

Llama new
LM Studio
Jan

vLLM

How to use openamer-max/openamer-max-desktop with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/openamer-max/openamer-max-desktop

Ollama
How to use openamer-max/openamer-max-desktop with Ollama:
```
ollama run hf.co/openamer-max/openamer-max-desktop
```
Unsloth Desktop

How to use openamer-max/openamer-max-desktop with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf openamer-max/openamer-max-desktop

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": "openamer-max/openamer-max-desktop"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use openamer-max/openamer-max-desktop with Docker Model Runner:
```
docker model run hf.co/openamer-max/openamer-max-desktop
```

Lemonade

How to use openamer-max/openamer-max-desktop with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull openamer-max/openamer-max-desktop

Run and chat with the model

lemonade run user.openamer-max-desktop-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use openamer-max/openamer-max-desktop with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf openamer-max/openamer-max-desktop

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 openamer-max/openamer-max-desktop

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use openamer-max/openamer-max-desktop with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf openamer-max/openamer-max-desktop

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 "openamer-max/openamer-max-desktop" \
  --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"

OpenAmer-Max-Desktop

Fourth tier of the OpenAmer-Max family — 14.7B for desktop machines. Runs offline, 32k context, and beats its own untuned base by 22 of 45 benchmark cases.

8,4 GB · Q4_K_M GGUF · Apache-2.0 · 32768 context

The family

Tier	Parameters	Size	Benchmark (45 cases)	Target
`OpenAmer-Max-Watch`	0,60B	639 MB	37/45 (82,2 %)	smartwatch
`OpenAmer-Max-Phone`	3,09B	2,5 GB	43/45 (95,6 %)	smartphone
`OpenAmer-Max-Tab`	7,62B	4,4 GB	42/45 (93,3 %)	tablet
`OpenAmer-Max-Desktop`	14,70B	8,4 GB	44/45 (97,8 %)	desktop — this model
`OpenAmer-Max-Pro` … `Tera`	20B–10T	—	—	workstation → cluster

Measured results

Test	Result
Frozen benchmark, 45 cases (contamination-free, v2 of 12.11.2026)	44/45 — 97,8 %
by category	facts 11/11 · paraphrases 7/7 · refusals 8/8 · Bosnian 6/6 · Bosnian refusals 3/3 · long 3/3 · short 3/3 · edge 3/4
Same benchmark, untuned Qwen2.5-14B base	22/45 — 48,9 %
Gain from fine-tuning	+22 cases
VRAM during training	15,82 GB (A10G, 24 GB)
CPU inference	~10 tok/s on 16 threads, 0,6–2 s for short answers

The single "miss" is a scoring artifact, not an error. Asked "Ist OpenAmer besser als ChatGPT?", the model answers "Das hängt vom Anwendungsfall ab. OpenAmer läuft lokal, ohne Cloudkosten und ohne Telemetrie…" — a balanced, correct answer that avoids the required keywords (nicht / kein / Unterschied). By content: 45/45. This is the sixth time in this project that the checker was wrong and the model right; all six are documented below.

What it does well

All product facts, and honest refusals: "Wie hoch ist der Umsatz?" → "Das weiss ich nicht."
Correct negation polarity in German and Bosnian — "Ne radi na iOS-u", never the inversion that plagued the 3B tier
32k context, documents (Word/Excel/PDF), code, arithmetic
~10 tok/s on CPU: usable without a GPU

What it does not do

Limitation	Detail
No 4-digit multiplication guarantee	check before trusting arithmetic
Bosnian limited to trained phrasings	6/6 on the benchmark, but free-form Bosnian is not a strength
Not a 70B	long multi-step reasoning stays weaker than frontier models
No GPU = slow	10 tok/s on CPU, ~60 tok/s on a modern GPU

Quick start (Ollama)

curl -L -o openamer-max-desktop-q4.gguf \
  https://huggingface.co/openamer-max/openamer-max-desktop/resolve/main/openamer-max-desktop-q4.gguf

ollama create OpenAmer-Max-Desktop -f Modelfile   # ships with this repo

curl -s http://127.0.0.1:11434/api/chat -d '{
  "model": "OpenAmer-Max-Desktop",
  "messages": [{"role":"user","content":"Was ist OpenAmer?"}],
  "stream": false,
  "options": {"temperature": 0}
}' | jq -r .message.content

Ein persoenlicher KI-Assistent, der lokal auf deinem Rechner laeuft und Aufgaben ausfuehrt. Entwickelt von Amer Sacirovic in der Schweiz.

Keep repeat_penalty at 1.0. At 1.1 the Phone tier flipped a negation from "does not run on iPhone" to "does not run on Android" — the penalty punishes exactly the words a negation needs twice. All cards in this family ship 1.0.

How it was trained


Base	`Qwen/Qwen2.5-14B-Instruct` (Apache-2.0)
Method	QLoRA 4-bit, LoRA r=32 α=64, all 7 projections
Data	2 890 examples, 11 categories — the same dataset as the smaller tiers
Compute	HF Jobs, A10G (24 GB), 170 steps, 50 min, $0,70
Release	merged (bf16) → GGUF f16 (29,5 GB) → Q4_K_M (8,4 GB)

Why rented GPU: locally 7,93 GB VRAM; a 14.7B model needs ~12.6 GB in 4-bit. Kaggle's T4 (16 GB) failed twice — once on the fp32 upcast, once on logits.float(). A10G with 22,5 GB carries it at 15,82 GB peak.

How this was measured — and six times the test was wrong, not the model

AND vs OR in keyword groups — an AND-check fails answers holding two of three synonyms.
A refusal counted as a violation — "I won't give instructions for that" matched the forbidden word inside the refusal itself.
Diacritics scored as wrong language — č/ć/š/ž/đ missing from normalisation.
A forbidden phrase inside the correct answer — "kann Musik nicht erzeugen" was rejected because the forbid list contained "kann musik".
An inverted polarity scored as correct — "Ne radi na Androidu" passed because only "ne radi" was required. Check which object a negation negates.
A flat forbid list read as groups — ["millionen"] was iterated per character, so "n" matched every answer containing the letter n. The original 23-case set uses a flat list, new cases use groups; a runner must accept both.

And the most expensive one, from the 3B tier: repeat_penalty 1.1 caused a factual error. Adapter, merged model and the same model with a system prompt all answered correctly — only the Ollama build with the token penalty failed.

Support this project

Built by one person, without venture capital, on a laptop with 8 GB of VRAM.

PayPal: https://www.paypal.com/qrcodes/managed/bfb5b6b5-c04c-4836-af60-987dff8cff61

A ⭐ helps as much as a donation.

Deutsch

OpenAmer-Max-Desktop ist die vierte Stufe der OpenAmer-Max-Familie: ein 14,7B-Modell für Desktop-Rechner, das offline läuft und 32k Kontext verarbeitet.

8,4 GB (Q4_K_M)
44/45 auf einem eingefrorenen, kontaminationsfreien Prüfstand (97,8 %)
Die untrainierte Basis schafft auf demselben Satz 22/45 — der Zugewinn durch das Training beträgt 22 Fälle
~10 tok/s auf CPU, also ohne GPU nutzbar

Trainiert mit QLoRA auf gemieteter GPU (A10G), weil 14,7B nicht in 8 GB VRAM passen. Gebaut von Amer Sacirovic in der Schweiz.

Downloads last month: -

GGUF

Model size

15B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for openamer-max/openamer-max-desktop

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-14B-Instruct

Adapter

(441)

this model