Instructions to use SwarmandBee/LocalLegal-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SwarmandBee/LocalLegal-27B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SwarmandBee/LocalLegal-27B",
	filename="locallegal-27b-q4.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SwarmandBee/LocalLegal-27B 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 SwarmandBee/LocalLegal-27B
# Run inference directly in the terminal:
llama cli -hf SwarmandBee/LocalLegal-27B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SwarmandBee/LocalLegal-27B
# Run inference directly in the terminal:
llama cli -hf SwarmandBee/LocalLegal-27B

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 SwarmandBee/LocalLegal-27B
# Run inference directly in the terminal:
./llama-cli -hf SwarmandBee/LocalLegal-27B

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 SwarmandBee/LocalLegal-27B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SwarmandBee/LocalLegal-27B

Use Docker

docker model run hf.co/SwarmandBee/LocalLegal-27B

LM Studio
Jan

vLLM

How to use SwarmandBee/LocalLegal-27B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SwarmandBee/LocalLegal-27B

Ollama
How to use SwarmandBee/LocalLegal-27B with Ollama:
```
ollama run hf.co/SwarmandBee/LocalLegal-27B
```

Unsloth Studio

How to use SwarmandBee/LocalLegal-27B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SwarmandBee/LocalLegal-27B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SwarmandBee/LocalLegal-27B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SwarmandBee/LocalLegal-27B to start chatting

How to use SwarmandBee/LocalLegal-27B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SwarmandBee/LocalLegal-27B

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SwarmandBee/LocalLegal-27B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SwarmandBee/LocalLegal-27B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SwarmandBee/LocalLegal-27B

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 SwarmandBee/LocalLegal-27B

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use SwarmandBee/LocalLegal-27B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SwarmandBee/LocalLegal-27B

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 "SwarmandBee/LocalLegal-27B" \
  --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"

Docker Model Runner
How to use SwarmandBee/LocalLegal-27B with Docker Model Runner:
```
docker model run hf.co/SwarmandBee/LocalLegal-27B
```

Lemonade

How to use SwarmandBee/LocalLegal-27B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SwarmandBee/LocalLegal-27B

Run and chat with the model

lemonade run user.LocalLegal-27B-{{QUANT_TAG}}

List all available models

lemonade list

LocalLegal-27B / README.md

SwarmandBee

Upload README.md with huggingface_hub

b0ea721 verified about 18 hours ago

preview code

Raw

History Blame Contribute Delete

5.54 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen3.6-27B
	language:
	- en
	pipeline_tag: text-generation
	library_name: gguf
	tags:
	- legal
	- consumer-protection
	- fdcpa
	- fcra
	- letter-writing
	- grant-writing
	- gguf
	- llama-cpp
	- ollama
	- qwen3
	- lora
	---

	# LocalLegal-27B

	A calm, dignified consumer-rights letter-writer & grant writer. It organizes the facts a person gives it and drafts clear, statute-grounded documents they can review, sign, and send themselves — debt-validation and cease-contact letters (FDCPA), credit-report disputes and method-of-verification letters (FCRA), goodwill and medical-billing letters, identity-theft blocks, and grant/assistance narratives.

	> This is document preparation, not legal advice. LocalLegal is not a lawyer, does not give legal advice, and never predicts the outcome of a case. It states what a statute says and what a letter requests — and hands anything past the letter stage (lawsuits, garnishment, liens, court dates) to free legal aid or a licensed attorney.

	Built by [Swarm & Bee](https://huggingface.co/SwarmandBee) — the brain behind the LocalLegal "write + send certified from home" flow.

	---

	## 🏆 It beat base — decisively, on both domains

	Stage-5 gate: held-out, per-domain, deterministic evaluation. Teacher-forced cross-entropy / perplexity on chat-templated eval, base vs cooked, same tokenizer & template, N=400/domain, seed 1117, seq 4096, bf16 on an RTX PRO 6000. No LLM-as-judge — a number anyone can re-derive.

	\| Domain \| Base ppl \| LocalLegal-27B ppl \| Δ \| Base CE → Cooked CE \|
	\|---\|--:\|--:\|--:\|---\|
	\| Legal (FDCPA/FCRA letters) \| 16.662 \| 2.058 \| −87.65% \| 2.813 → 0.722 \|
	\| Grant (proposal narratives) \| 3.250 \| 2.022 \| −37.80% \| 1.179 → 0.704 \|

	Beat base on both. Killed domains: none. Cooked CE (~0.70–0.72) matches the training landing (~0.64–0.77) → coherent, no overfit. The legal gain exceeds our DiabeticAnchor-27B reference (+57%). The 44%-share, 9%-truncation grant tail passed clean — not undercooked.

	Receipts (deterministic, re-runnable): `beat_base_27b.py` · `beat_base_27b.log` · `beat_base_27b_verdict.json`.

	---

	## 🔧 Usage

	This repo ships a Q4 GGUF (~16 GB) — runs on llama.cpp / Ollama / LM Studio. Qwen3.6 is a thinking model, so the chat template prefills an empty `<think>` block; the included `Modelfile` handles this for you.

	### Ollama
	```bash
	# with the included Modelfile (carries the template + system prompt + params)
	ollama create locallegal-27b -f locallegal-27b.Modelfile
	ollama run locallegal-27b "Draft an FDCPA debt-validation letter. Collector: Midland Credit. Account #4402, $1,284 medical debt I don't recognize."
	```

	### llama.cpp
	```bash
	./llama-cli -m locallegal-27b-q4.gguf -c 8192 --temp 0.6 --top-p 0.9 \
	-p "<your chat-templated prompt>"
	```

	Recommended sampling: `temperature 0.6`, `top_p 0.9`, `num_ctx 8192`. Stop tokens `<\|im_start\|>` / `<\|im_end\|>` (ChatML).

	### System prompt (its identity — every letter includes header, RE: line, statute cite, specific request, response window, signature block)
	The model is trained to the LocalLegal persona: calm, factual, never shaming, uses the verbs organize / draft / prepare / review / track, and refuses to say "legal advice," "sue them," "you'll win," or "guaranteed." Full system prompt ships in the `Modelfile`.

	---

	## 🍳 How it was cooked

	- Base: [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B) (Apache-2.0) — hybrid Gated-DeltaNet + Gated-Attention arch, thinking model.
	- Method: LoRA r32 / α16 on attn+mlp · LR 1e-5 · cosine · seq 4096 · bf16 · Unsloth + TRL. Clean 16-bit merge → Q4 GGUF.
	- Corpus: 78,231 train / 2,500 eval, curated down from ~340K raw rows via cross-domain dedup, eval carve-out, hash-scrub of contaminants, and near-dup pruning. Split Legal 57.8% / Grant 42.2% (natural balance, zero synthetic upsampling). Per-domain true holdout eval (legal 1,500 / grant 1,000).
	- Loss: 2.156 → 0.768 (−64%), smooth monotone, grad_norm 0.20 — textbook curve, no spikes/NaN, no overcook.
	- Rig: SwarmRails (owned) · 1× RTX PRO 6000 Blackwell 96 GB · 350 W thermal cap · 45.7 h wall. Sovereign compute — cooked on our own iron.
	- Discipline: full canary-then-cook (5-stage senior-hack review) — beat-base-or-kill, per domain, no blended half-truths.

	## 📁 Files
	- `locallegal-27b-q4.gguf` — Q4 quantized weights (~16 GB)
	- `locallegal-27b.Modelfile` — Ollama template + system prompt + params

	## 🔒 Defendable
	Every claim here has a receipt: deterministic per-domain beat-base eval (no LLM judge), monotone loss curve, hash-verified corpus, and a full cook flightsheet. Show the math, verify it yourself.

	## ⚖️ Scope & safety
	Document preparation only. Not legal advice, not a lawyer, no outcome predictions. Anything beyond the letter stage → free legal aid (LawHelp.org) / a licensed consumer-protection attorney / your state Attorney General. As a fine-tune of Qwen3.6-27B, it inherits the base model's Apache-2.0 terms and general LLM limitations (it can be wrong — a human reviews and signs every letter).

	## Citation
	```
	@misc{locallegal27b2026,
	title = {LocalLegal-27B: a statute-grounded consumer-rights letter-writer},
	author = {Swarm and Bee},
	year = {2026},
	note = {LoRA fine-tune of Qwen3.6-27B; deterministic per-domain beat-base eval},
	url = {https://huggingface.co/SwarmandBee/LocalLegal-27B}
	}
	```