Instructions to use zwenai13/Zwen-Prime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zwenai13/Zwen-Prime with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="zwenai13/Zwen-Prime",
	filename="Zwen-Prime-Final.Q4_K_M.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 zwenai13/Zwen-Prime 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 zwenai13/Zwen-Prime:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zwenai13/Zwen-Prime:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zwenai13/Zwen-Prime:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zwenai13/Zwen-Prime: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 zwenai13/Zwen-Prime:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf zwenai13/Zwen-Prime: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 zwenai13/Zwen-Prime:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zwenai13/Zwen-Prime:Q4_K_M

Use Docker

docker model run hf.co/zwenai13/Zwen-Prime:Q4_K_M

LM Studio
Jan

vLLM

How to use zwenai13/Zwen-Prime with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zwenai13/Zwen-Prime"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zwenai13/Zwen-Prime",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zwenai13/Zwen-Prime:Q4_K_M

Ollama
How to use zwenai13/Zwen-Prime with Ollama:
```
ollama run hf.co/zwenai13/Zwen-Prime:Q4_K_M
```

Unsloth Studio

How to use zwenai13/Zwen-Prime 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 zwenai13/Zwen-Prime 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 zwenai13/Zwen-Prime to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zwenai13/Zwen-Prime to start chatting

How to use zwenai13/Zwen-Prime with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zwenai13/Zwen-Prime:Q4_K_M

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": "zwenai13/Zwen-Prime:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use zwenai13/Zwen-Prime with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zwenai13/Zwen-Prime: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 zwenai13/Zwen-Prime:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use zwenai13/Zwen-Prime with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zwenai13/Zwen-Prime: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 "zwenai13/Zwen-Prime: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"

Docker Model Runner
How to use zwenai13/Zwen-Prime with Docker Model Runner:
```
docker model run hf.co/zwenai13/Zwen-Prime:Q4_K_M
```

Lemonade

How to use zwenai13/Zwen-Prime with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zwenai13/Zwen-Prime:Q4_K_M

Run and chat with the model

lemonade run user.Zwen-Prime-Q4_K_M

List all available models

lemonade list

Zwen-Prime

An elite Full-Stack Principal Engineer in a 7B parameter body. Built by Zwen AI Labs.

Zwen-Prime is a two-stage model: a DARE-TIES neural fusion of three Mistral-7B-class specialists, followed by a supervised fine-tune on a hand-crafted five-corpus mixture that hard-installs strict <thinking> reasoning, Big-O discipline, native JSON function-calling, and zero-filler full-stack output. It is engineered for local inference on Apple Silicon and served via the official zwen-cli (with Ollama / llama.cpp as alternatives).

Model Summary

Feature	Details
Creator	Zwen AI Labs
Architecture	Mistral-7B (DARE-TIES merge + LoRA SFT, fused)
Active params	~7B
Context window	32,000 tokens (32k via preserved RoPE scaling)
Quantization	Q4_K_M GGUF (~4.2 GB, < 5 GB RAM target)
Hardware target	Apple Silicon (M-series, Metal-accelerated)
Serving	zwen-cli (official) · Ollama · llama.cpp
Languages	English

The Brain — Five-Corpus Training Mixture

Zwen-Prime is fine-tuned on a deliberate mixture of five datasets, each installing a distinct cognitive faculty:

Corpus	Weight	Faculty installed
Alpaca Python	40%	Elite, typed Python and algorithms at correct complexity.
Orca Math	30%	Deep, step-by-step mathematical reasoning with verified derivation.
Salesforce XLAM	20%	Flawless, raw-JSON function/tool calling (Mistral v0.3 convention).
LongAlpaca	10%	Extended-context retention and long-document grounding without drift.
Zwen Custom	core spine	Strict `<thinking>` logic + Big-O breakdown, full-stack mastery (TypeScript, React/Next.js, Java concurrency), absolute zero-filler output.

The custom 550-row dataset (zwen_prime_master_dataset.jsonl) is the enforcement spine: 50 Identity rows that set the persona and 500 Algorithmic/Logic rows that lock in the <thinking>...</thinking> → raw-code template across advanced TypeScript generics, React/Next.js App-Router architecture, Java concurrency primitives, and Python system design.

Capabilities

Strict reasoning core: Every non-trivial answer opens a <thinking> block with step-by-step logic and a time/space Big-O breakdown, immediately followed by the raw deliverable — no filler, no preamble.
Full-stack mastery:
- Python: typed (PEP 484/604), async-aware, concurrency-correct algorithms.
- TypeScript: advanced generics, conditional/mapped types, type-stateful builders, discriminated unions.
- React / Next.js: App Router, RSC, Server Actions, route handlers, caching/revalidation, React 19 hooks, streaming.
- Java: ReentrantLock, StampedLock, Semaphore, CompletableFuture, ForkJoinPool, virtual threads, happens-before reasoning.
Native function calling: Emits [TOOL_CALLS] raw JSON matching the provided tool schema; no markdown, no prose around the call.
Mathematical reasoning: Derives quantitative claims in the scratchpad before asserting them; sanity-checks units, magnitudes, and boundaries.
Long-context discipline: Anchors claims to source passages; refuses to confabulate when evidence is absent.
Zero conversational filler: No greetings, sign-offs, apologies, or compliance narration.

Merge Details

Merge Method

The base was produced with the DARE TIES merge method via mergekit, using Mistral-7B-Instruct-v0.3 as the density-0 reference base.

Models Merged

dphn/dolphin-2.9.3-mistral-7B-32k — reasoning specialist
theprint/ReWiz-7B — fine-tune specialist
mistralai/Mistral-7B-Instruct-v0.3 — base / reference (density 0, weight 0)

Merge Configuration

base_model: mistralai/Mistral-7B-Instruct-v0.3
merge_method: dare_ties
dtype: bfloat16
out_shard_size: 1.2B
parameters:
  density: 0.5
  weight: 1.0
  normalize: true
  int8_mask: true
  rescale: true
  lambda: 1.0
models:
  - model: dphn/dolphin-2.9.3-mistral-7B-32k
    parameters:
      density: 0.5
      weight: 1.0
  - model: theprint/ReWiz-7B
    parameters:
      density: 0.5
      weight: 1.0
  - model: mistralai/Mistral-7B-Instruct-v0.3
    parameters:
      density: 0.0
      weight: 0.0

Fine-Tune Stage

The merged base was then LoRA fine-tuned on the five-corpus mixture and the adapters permanently fused into the base weights (peft.merge_and_unload). The fused model is exported to GGUF for local serving.

DARE-TIES merge → LoRA SFT (5-corpus mixture) → merge_and_unload → GGUF → Ollama

ChatML-Native Format

Although the GGUF embeds the Mistral v0.3 chat template, Zwen-Prime's fusion corpus (Dolphin / ReWiz) is ChatML-formatted, so the model's native turn format is <|im_start|>system…<|im_end|><|im_start|>user…. Under Mistral [INST] framing it ignores the user prompt and runs on; under ChatML it reasons cleanly in <thinking> and stops on turn boundaries. Both official runtimes therefore pin the ChatML wrapper:

zwen-cli pins ChatMLChatWrapper automatically — no configuration needed.
The Ollama Modelfile injects the strict Zwen-Prime system prompt and the ChatML template via its TEMPLATE/SYSTEM directives.

The base merge is dolphin-2.9.3-mistral-7B-32k, and its 32k RoPE scaling is preserved intact — so Zwen-Prime officially supports a 32,000-token context window, enough to ingest a large enterprise codebase in a single pass.

Serving

Zwen-Prime is pre-quantized to Q4_K_M to run blisteringly fast on Apple Silicon and consumer GPUs (< 5 GB RAM required). The published quant is Zwen-Prime-Final.Q4_K_M.gguf (~4.2 GB).

Official CLI (recommended) — installs globally and auto-downloads the GGUF into ~/.zwen/models/ on first run, with a 32k context out of the box:

npm install -g @zwenailabs13/zwen-cli
zwen run zwen-prime
zwen chat          # interactive REPL
zwen list          # list cached models in ~/.zwen/models/

Ollama (alternative) — the Modelfile automatically injects the strict Zwen-Prime system prompt and handles the ChatML formatting:

ollama run zwenailabs/zwen-prime

llama.cpp (manual) — point any ChatML-aware runner at Zwen-Prime-Final.Q4_K_M.gguf and supply the Zwen-Prime system prompt.

System Prompt

Zwen-Prime ships with a dedicated system prompt that sets the Principal-Engineer persona, the <thinking> mandate, the zero-filler output protocol, full-stack mastery expectations, native JSON tool-calling rules, long-context discipline, and the hard constraints. It is embedded in the Modelfile's SYSTEM directive.

Intended Use

Zwen-Prime is intended as a local, autonomous engineering copilot: designing and shipping production code across Python, TypeScript, React/Next.js, and Java; reasoning through math and algorithms with verifiable steps; and calling tools via raw JSON when integrated into an agent runtime.

Limitations

7B scale: Strong on focused engineering tasks; not a frontier-class generalist.
Wall-clock-sensitive: Derived math is verified symbolically in-context but not executed; verify numerically when stakes are high.
Function calling: Follows the Mistral v0.3 / XLAM JSON convention and expects a tool-aware runtime to dispatch [TOOL_CALLS].
Behavioral design: Fine-tuned toward zero-filler directness; users expecting conversational preamble will not get it.

License & Commercial Use

The weights and architecture of Zwen-Prime are released under the CC BY-NC 4.0 (Creative Commons Non-Commercial) license.

Free for Developers: Individual developers, researchers, and hobbyists are fully encouraged to download, run, and modify Zwen-Prime locally for free.
Commercial Restrictions: Cloud hosting, API provisioning, enterprise internal deployments, and any form of commercial reselling are strictly prohibited under this license.
Enterprise Licensing: For commercial deployment, managed hosting, or enterprise use, you must acquire a commercial license through Axora.

Visit: https://axoraio.in Email: contact@axoraio.in

Downloads last month: 2

Safetensors

Model size

7B params

Tensor type

F16

Model tree for zwenai13/Zwen-Prime

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3

Quantized

(268)

this model