Instructions to use n4ze3m/assistllm-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use n4ze3m/assistllm-v0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="n4ze3m/assistllm-v0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("n4ze3m/assistllm-v0")
model = AutoModelForCausalLM.from_pretrained("n4ze3m/assistllm-v0", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use n4ze3m/assistllm-v0 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 n4ze3m/assistllm-v0:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf n4ze3m/assistllm-v0:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf n4ze3m/assistllm-v0:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf n4ze3m/assistllm-v0: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 n4ze3m/assistllm-v0:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf n4ze3m/assistllm-v0: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 n4ze3m/assistllm-v0:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf n4ze3m/assistllm-v0:Q4_K_M

Use Docker

docker model run hf.co/n4ze3m/assistllm-v0:Q4_K_M

LM Studio
Jan

vLLM

How to use n4ze3m/assistllm-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "n4ze3m/assistllm-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "n4ze3m/assistllm-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/n4ze3m/assistllm-v0:Q4_K_M

SGLang

How to use n4ze3m/assistllm-v0 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "n4ze3m/assistllm-v0" \
    --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": "n4ze3m/assistllm-v0",
		"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 "n4ze3m/assistllm-v0" \
        --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": "n4ze3m/assistllm-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use n4ze3m/assistllm-v0 with Ollama:
```
ollama run hf.co/n4ze3m/assistllm-v0:Q4_K_M
```

Unsloth Studio

How to use n4ze3m/assistllm-v0 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 n4ze3m/assistllm-v0 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 n4ze3m/assistllm-v0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for n4ze3m/assistllm-v0 to start chatting

How to use n4ze3m/assistllm-v0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf n4ze3m/assistllm-v0: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": "n4ze3m/assistllm-v0:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use n4ze3m/assistllm-v0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf n4ze3m/assistllm-v0: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 "n4ze3m/assistllm-v0: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 n4ze3m/assistllm-v0 with Docker Model Runner:
```
docker model run hf.co/n4ze3m/assistllm-v0:Q4_K_M
```

Lemonade

How to use n4ze3m/assistllm-v0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull n4ze3m/assistllm-v0:Q4_K_M

Run and chat with the model

lemonade run user.assistllm-v0-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use n4ze3m/assistllm-v0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf n4ze3m/assistllm-v0: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 n4ze3m/assistllm-v0:Q4_K_M

Run Hermes

hermes

Atomic Chat

Assist-LLM v0

A ~150M-parameter tool-calling model, trained from scratch for less than the cost of a meal.
_{DeepSeek-V3-style MLA + MoE · no thinking mode · 337MB · runs on a phone · total GPU bill ≈ 2.7 burgers}

Assist-LLM v0 is a tiny agentic model built for Page Assist — it chats, and more importantly it calls tools: given function schemas, it decides whether to call, extracts arguments as JSON, stops cleanly, and grounds its answer in the tool's response.

It was trained from a random initialization on a single rented RTX 5090 — pretraining, SFT, calibration, evals and all — for ~$14 total. The entire pipeline is open: data manifest → tokenizer → pretrain → SFT → calibration → benchmarks. Knowledge cutoff: early 2026 (it will tell you this itself if asked).

Benchmarks (0-shot)

Benchmark	Score	Random
BoolQ	60.0	50.0
PIQA	58.0	50.0
When2Call (tool-judgment MCQ)	51.1	25.0
WinoGrande	50.1	50.0
ARC-Easy	37.9	25.0
SocialIQA	35.6	33.3
HellaSwag (acc_norm)	27.4	25.0
OpenBookQA (acc_norm)	26.2	25.0
ARC-Challenge	19.9	25.0

All via lm-evaluation-harness, 0-shot; When2Call via NVIDIA's MCQ configs adapted to this model's chat format.

Read these numbers honestly: this is a 150M model pretrained on 800M tokens (models like SmolLM2-135M use 2T). General-knowledge MCQ is its weakest suit — it is not what the model is for. The model's job is the tool-calling protocol, and there it performs:

Behavioral probe (greedy)	Result
Emits `<tool_call>` with valid JSON args, correct tool	✅
Terminates cleanly at `<\|im_end\|>`	✅
Doesn't call tools for math/trivia/small factual questions	✅
Asks a short clarification when a required argument is missing	✅
Grounds the final answer in the tool's response	✅
Knows its name, creator, and cutoff	✅
Doesn't call tools for pure social chit-chat ("hi", "thanks")	❌ known bug

The bill (in burgers)

Pretrain 3.1h + SFT 6h + calibration ~0.6h + evals ~1h on one RTX 5090 at $0.524/h, plus a few false starts on slower boxes. Frontier labs measure training runs in GDP; this one is lunch.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("n4ze3m/assistllm-v0")
model = AutoModelForCausalLM.from_pretrained("n4ze3m/assistllm-v0", dtype=torch.bfloat16, device_map="cuda")

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get current weather for a city.",
        "parameters": {"type": "object",
                       "properties": {"city": {"type": "string"}},
                       "required": ["city"]},
    },
}]

messages = [{"role": "user", "content": "weather in Kochi?"}]
enc = tok.apply_chat_template(messages, tools=tools, add_generation_prompt=True,
                              tokenize=True, return_dict=True, return_tensors="pt").to("cuda")
out = model.generate(**enc, max_new_tokens=80, do_sample=False,
                     eos_token_id=tok.convert_tokens_to_ids("<|im_end|>"))
print(tok.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=False))

<tool_call>
{"name": "get_weather", "arguments": {"city": "Kochi"}}
</tool_call><|im_end|>

Feed the tool result back as a {"role": "tool", "content": ...} message and it answers from it.

GGUF (llama.cpp) — experimental

Shipped in this repo, quantized from the bf16 weights:

File	Size	Use
`gguf/assistllm-v0-q4_k_m.gguf`	128MB	phones, browsers, Raspberry Pi
`gguf/assistllm-v0-q8_0.gguf`	172MB	near-lossless local
`gguf/assistllm-v0-bf16.gguf`	323MB	reference

llama-cli -m assistllm-v0-q4_k_m.gguf -no-cnv

⚠️ Experimental: the GGUF path (llama.cpp/Ollama) chats fine and keeps the identity, but the tool-call trigger is less reliable than the transformers path — llama.cpp's DeepSeek-MLA implementation assumes the flagship's head dims, and this model's custom dims (10 heads, nope/rope 96/32) sit slightly off that math. For dependable tool calling use the safetensors weights (above). An Ollama Modelfile with the correct ChatML Go-template is included at ollama/Modelfile.

Architecture

DeepSeek-V3-style, scaled to pocket size — 168M total / ~80M active parameters:

MLA (Multi-head Latent Attention) — compressed KV cache, cheap long context
DeepSeekMoE — fine-grained experts, most parameters asleep per token
32k BPE tokenizer (trained on the pretrain corpus), 4096 context
ChatML-style format with <tools> / <tool_call> / <tool_response>; assistant-only loss via {% generation %} blocks
No thinking mode — it just answers

Training

Stage	Data	Tokens/rows	Time	Loss
A · pretrain	FineWeb-Edu + Wikipedia + Cosmopedia	800M tokens	3.1h	3.31
B+C · SFT	SmolTalk, general-knowledge QA, identity set, Hermes function-calling, Aquila deepsearch, bash tool, When2Call, GSM8K math, Python code	325,659 convos	6h	1.87
D · calibration	judgment-tilted mix: no-call / clarify / extraction + identity oversample + replay	24,703 convos	21min	1.20

Stage D exists because v0.9 over-triggered: with tools in context it called them for everything, echoing the schema ({"city": "city"}) when it couldn't extract an argument — the exact pathology NVIDIA's When2Call work describes ("public datasets contain many examples of calling tools but far fewer of not calling them"). One calibration pass later: judgment fixed, identity learned, social chit-chat still trigger-happy (see below).

Known limitations

Weak general knowledge, math, and prose. 150M params × 800M tokens — give it tools, that's the point.
Social over-triggering: "hi" / "thanks" with tools in context may produce a spurious call with a placeholder argument. App-layer guard: reject any argument value that literally equals its schema property name and treat the turn as chat.
English-only, text-only, no vision.
This is a research artifact, not a production assistant. Verify anything that matters.

License

Model weights and code: Apache 2.0. Training data remains under its original datasets' licenses.

Use of LLMs

We leverage large language models (LLMs) to assist in drafting and polishing written content. Specifically, LLMs are used to improve clarity, coherence, and readability of the text, while ensuring that technical accuracy and intended meaning are preserved. All outputs generated by the LLM are carefully reviewed and edited by the authors to maintain factual correctness and align with the scientific content. The LLM serves as a tool to support writing efficiency, not to generate original research ideas or conclusions.

Citation

@misc{assistllm-v0,
  title  = {Assist-LLM v0: a 150M tool-calling model trained for less than a meal},
  author = {Muhammed Nazeem (n4ze3m), Page Assist},
  year   = {2026},
  url    = {https://huggingface.co/n4ze3m/assistllm-v0}
}

Downloads last month: -

Safetensors

Model size

0.2B params

Tensor type

F32

BF16

n4ze3m
/

assistllm-v0

Assist-LLM v0

Benchmarks (0-shot)

The bill (in burgers)

Usage

GGUF (llama.cpp) — experimental

Architecture

Training

Known limitations

License

Use of LLMs

Citation

Space using n4ze3m/assistllm-v0 1