Like 0

Text Generation

Transformers

Safetensors

GGUF

5 languages

qwen3

agentic

tool-calling

function-calling

mcp

react

on-device

local-first

offline

edge-ai

small-language-model

slm

ollama

llama.cpp

nigeria

nigerian

pidgin

conversational

text-generation-inference

License: apache-2.0

Model card Files Files and versions xet

Community 1

Deploy

Copy to bucket

Use this model Instructions to use Erog0291/stewmind-1.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers How to use Erog0291/stewmind-1.7b with Transformers:

Use a pipeline as a high-level helper

from transformers import pipeline

pipe = pipeline("text-generation", model="Erog0291/stewmind-1.7b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)

pip install -U transformers accelerate

Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Erog0291/stewmind-1.7b") model = AutoModelForCausalLM.from_pretrained("Erog0291/stewmind-1.7b", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks

Google Colab

Kaggle

Local Apps Settings

llama.cpp How to use Erog0291/stewmind-1.7b with llama.cpp:

curl -LsSf https://llama.app/install.sh | sh

Start a local OpenAI-compatible server with a web UI:

llama serve -hf Erog0291/stewmind-1.7b:Q4_K_M

Run inference directly in the terminal:

llama cli -hf Erog0291/stewmind-1.7b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp

Start a local OpenAI-compatible server with a web UI:

llama serve -hf Erog0291/stewmind-1.7b:Q4_K_M

Run inference directly in the terminal:

llama cli -hf Erog0291/stewmind-1.7b: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 Erog0291/stewmind-1.7b:Q4_K_M

Run inference directly in the terminal:

./llama-cli -hf Erog0291/stewmind-1.7b: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 Erog0291/stewmind-1.7b:Q4_K_M

Run inference directly in the terminal:

./build/bin/llama-cli -hf Erog0291/stewmind-1.7b:Q4_K_M

Use Docker

docker model run hf.co/Erog0291/stewmind-1.7b:Q4_K_M

Llama new

LM Studio

Jan

vLLM How to use Erog0291/stewmind-1.7b with vLLM:

Install vLLM from pip:

pip install vllm

Start the vLLM server:

vllm serve "Erog0291/stewmind-1.7b"

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:8000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "Erog0291/stewmind-1.7b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Use Docker

docker model run hf.co/Erog0291/stewmind-1.7b:Q4_K_M

SGLang How to use Erog0291/stewmind-1.7b with SGLang:

Install SGLang from pip:

pip install sglang

Start the SGLang server:

python3 -m sglang.launch_server
--model-path "Erog0291/stewmind-1.7b"
--host 0.0.0.0
--port 30000

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:30000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "Erog0291/stewmind-1.7b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Use Docker images

docker run --gpus all
--shm-size 32g
-p 30000:30000
-v ~/.cache/huggingface:/root/.cache/huggingface
--env "HF_TOKEN=<secret>"
--ipc=host
lmsysorg/sglang:latest
python3 -m sglang.launch_server
--model-path "Erog0291/stewmind-1.7b"
--host 0.0.0.0
--port 30000

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:30000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "Erog0291/stewmind-1.7b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Ollama How to use Erog0291/stewmind-1.7b with Ollama:

ollama run hf.co/Erog0291/stewmind-1.7b:Q4_K_M

Unsloth Desktop

Pi How to use Erog0291/stewmind-1.7b with Pi:

Install llama.cpp:

brew install llama.cpp

Start a local OpenAI-compatible server:

llama serve -hf Erog0291/stewmind-1.7b: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": "Erog0291/stewmind-1.7b:Q4_K_M" } ] } } }

Run Pi

Start Pi in your project directory:

pi

Docker Model Runner How to use Erog0291/stewmind-1.7b with Docker Model Runner:

docker model run hf.co/Erog0291/stewmind-1.7b:Q4_K_M

Lemonade How to use Erog0291/stewmind-1.7b with Lemonade:

Download Lemonade from https://lemonade-server.ai/

lemonade pull Erog0291/stewmind-1.7b:Q4_K_M

Run and chat with the model

lemonade run user.stewmind-1.7b-Q4_K_M

List all available models

lemonade list

Hermes Agent How to use Erog0291/stewmind-1.7b with Hermes Agent:

Install llama.cpp:

brew install llama.cpp

Start a local OpenAI-compatible server:

llama serve -hf Erog0291/stewmind-1.7b: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 Erog0291/stewmind-1.7b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw How to use Erog0291/stewmind-1.7b with OpenClaw:

Install llama.cpp:

brew install llama.cpp

Start a local OpenAI-compatible server:

llama serve -hf Erog0291/stewmind-1.7b: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 "Erog0291/stewmind-1.7b: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"

StewMind 1.7B 🇳🇬 — The Tiny Agentic Brain That Runs on YOUR Machine Real Evaluation (measured, not marketing)

StewMind vs the giants (our measured numbers + publicly listed specs)

Quick start

What's next: StewMind 1.7B ULTRA

StewMind 1.7B 🇳🇬 — The Tiny Agentic Brain That Runs on YOUR Machine

Big models cook for everyone. This one cooks for you.

StewMind 1.7B is a compact agentic AI built in Nigeria. It routes intents, calls tools, plans with ReAct and stores memory — locally, offline, with zero API bills.

Real Evaluation (measured, not marketing)

We ran StewMind 1.7B live on a plain CPU (no GPU) across 5 agentic tasks. Raw results are published in benchmark_results.json.

Tool-routing test — input: "Send 5000 naira to my brother today. Reply with only a JSON object." StewMind answered:

{"tool": "transfer", "args": {"amount": "5000", "recipient": "my brother", "date": "today"}}

Valid JSON. Correct tool. Correct arguments. On a CPU.

Measured on CPU (fp32, unquantized, shared sandbox):

StewMind vs the giants (our measured numbers + publicly listed specs)

StewMind 1.7B GPT-4o-mini (API) Llama-3.1-8B Phi-3.5-mini

Runs offline ✅ 100% local ❌ needs internet ✅ ✅

Data leaves your device Never Always Never Never

Download size ~1 GB (GGUF) 0 (API only) ~4.7 GB (Q4) ~2.3 GB (Q4)

RAM to run ~1.5 GB n/a ~6 GB ~3 GB

Cost per 1M tokens $0.00 forever ~$0.15–0.60 (listed) $0.00 $0.00

First-token latency ms (on-device) ~500-2000 ms network ms ms

Fits in a phone ✅ ❌ ❌ barely

A 1.7B will not out-write GPT-4. It doesn't have to. Agents need routing, tool calls and reflexes — and there StewMind wins on speed, cost and privacy. NVIDIA's own research ("Small Language Models are the Future of Agentic AI") points exactly this way.

Quick start

from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("Erog0291/stewmind-1.7b") model = AutoModelForCausalLM.from_pretrained("Erog0291/stewmind-1.7b") msgs = [{"role": "user", "content": "Call the weather tool for Lagos. JSON only."}] ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt") print(tok.decode(model.generate(ids, max_new_tokens=80, do_sample=False)[0][ids.shape[1]:], skip_special_tokens=True))

GGUF (Ollama / llama.cpp): download stewmind-1.7b-Q4_K_M.gguf from this repo — ready to run on phones, laptops and edge devices.

What's next: StewMind 1.7B ULTRA

ULTRA is training right now on 100,000 agentic workflow samples (tool calls, ReAct traces, memory ops) — checkpoints land in Erog0291/stewmind-1.7b-ultra as they bake. Expect sharper, faster, stricter-JSON agents.

Read the launch story: Big Models Cook for Everyone. This One Cooks for You.

Built with 🍲 in Nigeria by MUTYINT · Apache 2.0 · commercial use allowed

","pad_token":"<|endoftext|>","unk_token":null},"chat_template_jinja":"{%- if tools %}\n {{- '<|im_start|>system\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\n\n' }}\n {%- endif %}\n {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}\n {%- for tool in tools %}\n {{- "\n" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}\n {%- elif message.role == "assistant" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last