Instructions to use R3n3r0/dapack-language with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use R3n3r0/dapack-language 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 R3n3r0/dapack-language
# Run inference directly in the terminal:
llama cli -hf R3n3r0/dapack-language

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf R3n3r0/dapack-language
# Run inference directly in the terminal:
llama cli -hf R3n3r0/dapack-language

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 R3n3r0/dapack-language
# Run inference directly in the terminal:
./llama-cli -hf R3n3r0/dapack-language

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 R3n3r0/dapack-language
# Run inference directly in the terminal:
./build/bin/llama-cli -hf R3n3r0/dapack-language

Use Docker

docker model run hf.co/R3n3r0/dapack-language

LM Studio
Jan

vLLM

How to use R3n3r0/dapack-language with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "R3n3r0/dapack-language"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "R3n3r0/dapack-language",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/R3n3r0/dapack-language

Ollama
How to use R3n3r0/dapack-language with Ollama:
```
ollama run hf.co/R3n3r0/dapack-language
```
Unsloth Desktop

How to use R3n3r0/dapack-language with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf R3n3r0/dapack-language

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": "R3n3r0/dapack-language"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use R3n3r0/dapack-language with Docker Model Runner:
```
docker model run hf.co/R3n3r0/dapack-language
```

Lemonade

How to use R3n3r0/dapack-language with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull R3n3r0/dapack-language

Run and chat with the model

lemonade run user.dapack-language-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use R3n3r0/dapack-language with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf R3n3r0/dapack-language

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 R3n3r0/dapack-language

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use R3n3r0/dapack-language with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf R3n3r0/dapack-language

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 "R3n3r0/dapack-language" \
  --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"

dapack — language pack (graded precision, 10.7 GB)

Qwen3.5-35B-A3B compressed for language and general-text work: 10.7 GB instead of 21.2 GB, with every expert still present. The 143 experts this domain routes to are kept at q2_K; the remaining 113 are held at IQ2_XXS (2.06 bpw) under an importance matrix — graded, not deleted, so the pack degrades out of domain instead of breaking.

⚠️ This file requires the dapack runtime

Graded packs carry two expert tensors per layer at different precisions (ffn_*_exps_cold + dapack.hot_experts_per_layer). Stock llama.cpp / ollama / LM Studio cannot load them. Build the runtime from:

https://github.com/R3n3r0/dapack — ready-to-run binaries under Releases (Linux x86_64, ROCm), nothing to compile:
tar xzf dapack-v0.1.0-linux-x86_64-rocm-gfx1151.tar.gz
cd dapack-v0.1.0-* && ./dapack serve ~/catalog.dapack   # web chat + OpenAI API + routing
On other GPUs, build from the same repo (one command, scripts/rebuild_fork.sh --apply after a recursive clone).

Measured capabilities

These numbers are behavioural measurements, not estimates. They ship in the pack's manifest, and the dapack router treats them as hard constraints — a request needing a capability this pack has lost is routed to a pack that has it.

capability	this pack	full model (21.2 GB)
reasoning (GSM8K convergence, 4096-token budget, n=100)	82.0%	77.0%
tool calling (8 probes)	8/8	8/8
translation en→it	100%	100%
instruction following	100%	80%
long context (needle @ 3k tokens)	100%	100%
structured output (JSON)	100%	100%
code generation	17% ⚠️	100%

What it lost — on purpose, and declared: code generation collapsed (100% → 17%), because the experts that write code were held at 2 bits by a language calibration. Under the dapack router, code requests never reach this pack. If you serve this file standalone, do not use it for code.

Why graded instead of pruned

On the identical expert selection, we measured:

mechanism	Qwen3.5-35B	Qwen3-30B	tools
surplus experts deleted	79.0%	40.0%	7/8
surplus experts at 2 bits	82.0%	93.3%	8/8

On the second architecture deletion loses 53 points and grading loses none — 93.3% equals the uncompressed base. Measured on two models, same selection.

Deletion costs ~1 point of reasoning per 1% of experts chosen wrongly and is unrecoverable. A 2-bit expert is present and merely imprecise. Compute cost is unchanged: the top-k budget is partitioned across the two banks, so exactly 8 experts run per token.