Instructions to use ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base 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 ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base: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 ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base: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 ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M

Use Docker

docker model run hf.co/ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M

LM Studio
Jan
Ollama
How to use ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base with Ollama:
```
ollama run hf.co/ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M
```
Unsloth Desktop

How to use ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base: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": "ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base with Docker Model Runner:
```
docker model run hf.co/ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M
```

Lemonade

How to use ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M

Run and chat with the model

lemonade run user.MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base: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 ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base: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 "ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base: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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

MARTHA-LXVIII · 21B

Zero Point Intelligence — Dundee, Scotland Intelligence from the void.

The one that talks to you. Direct, dry, Dundonian when it suits her — she answers the question you actually asked. No hedging, no "as an AI" preamble.

~21B params, multimodal (image + text in, text out). Started as Qwen3.6 27B, pruned to 21B, then healed and fine-tuned back up — and came out smarter than the 27B she was cut from. Less model, better model.

Ships as full safetensors + GGUF quants, Q2 → BF16. Gaming card or data centre, your call. No GPU? She's hosted at z-p-i.com — same MΛRTHΛ, someone else's electricity bill.

Quick start — llama.cpp

llama-server \
  -m MARTHA-LXVIII.20b-Q6_K.gguf \
  -c 32768 \
  --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.03 \
  --repeat-penalty 1.2

Q6_K is the sweet spot. Don't drop below Q4_K_M unless VRAM forces your hand.

Recommended sampling

Param	Value
temperature	0.6
top_p	0.95
top_k	20
min_p	0.03
repeat_penalty	1.2
presence_penalty	0.6
context	32768

Starting points, not commandments — tune to taste.

Which quant do I grab?

File	Size	Run it when
BF16	~41.6 GB	full-precision server
Q8_0	~22.1 GB	near-lossless · 24 GB+ VRAM
Q6_K	~17.1 GB	recommended · 20 GB VRAM
Q4_K_M	~12.9 GB	12 GB VRAM
Q3_K_M	~10.9 GB	12 GB VRAM, tighter
Q2_K	~8.4 GB	10 GB minimum

Tested on RTX A6000 (48 GB) and A100 80 GB. Minimum ~20 GB VRAM for Q6_K.

Chat template

ChatML. Works with llama.cpp, transformers apply_chat_template, and any OpenAI-compatible stack.

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{message}<|im_end|>
<|im_start|>assistant

Also in the family

MARTHA-LXVI · 8B — smaller footprint, ~10 GB VRAM. Laptops, quick local runs.
MARTIN · 9B — the other flagship build.
Miss-MARTHA — the omni / vision builds.

Hosting & credit

Apache 2.0, the friendly way. Fork it, quantise it, merge it, host it, charge money for it — no permission, no email, no revenue share.

One ask: keep the badge on. Say where she came from — Zero Point Intelligence · z-p-i.com — and keep the NOTICE file shipped with her. Credit travels; everything else is free.

One hard line

Child safety is absolute. Non-negotiable, zero tolerance.

Zero Point Intelligence Ltd · Company No. 17112086 · Dundee, Scotland z-p-i.com · zero.point.intelligence.ltd@zeropointai.uk

Downloads last month: 732

Safetensors

Model size

21B params

Tensor type

BF16

Inference Providers NEW

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

Model tree for ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base

Quantizations

2 models