Instructions to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF",
	filename="Kai-0.35B-Instruct.IQ3_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF: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 Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF: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 Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M

SGLang

How to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF 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 "Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF" \
    --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": "Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF",
		"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 "Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF" \
        --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": "Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF with Ollama:
```
ollama run hf.co/Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF 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 Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF 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 Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF to start chatting

Docker Model Runner
How to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.NoesisLab-Kai-0.35B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

GGUF Files for Kai-0.35B-Instruct

These are the GGUF files for NoesisLab/Kai-0.35B-Instruct.

Downloads

GGUF Link	Quantization	Description
Download	Q2_K	Lowest quality
Download	Q3_K_S
Download	IQ3_S	Integer quant, preferable over Q3_K_S
Download	IQ3_M	Integer quant
Download	Q3_K_M
Download	Q3_K_L
Download	IQ4_XS	Integer quant
Download	Q4_K_S	Fast with good performance
Download	Q4_K_M	Recommended: Perfect mix of speed and performance
Download	Q5_K_S
Download	Q5_K_M
Download	Q6_K	Very good quality
Download	Q8_0	Best quality
Download	f16	Full precision, don't bother; use a quant

Note from Flexan

I provide GGUFs and quantizations of publicly available models that do not have a GGUF equivalent available yet, usually for models I deem interesting and wish to try out.

If there are some quants missing that you'd like me to add, you may request one in the community tab. If you want to request a public model to be converted, you can also request that in the community tab. If you have questions regarding this model, please refer to the original model repo.

You can find more info about me and what I do here.

Kai-0.35B-Instruct

A compact 0.35B-parameter instruction-tuned language model optimized for reasoning, math, and code generation tasks.

Model Details


Model	Kai-0.35B-Instruct
Architecture	LlamaForCausalLM
Parameters	360M
Hidden size	960
Layers	32
Attention heads	15 (5 KV heads, GQA)
Context length	8192
Precision	bfloat16
Vocab size	49,152

Benchmark Results (5-shot, log-likelihood)

Benchmark	Kai-0.35B-Instruct	Mamba (370M)	TinyLlama (1.1B)	Llama-3.2 (1B)
ARC-Challenge (science reasoning)	37.80%	~29.1%	~30.1%	~44.5%
HellaSwag (sentence completion)	55.88%	~53.8%	~59.2%	~61.1%
PIQA (physical commonsense)	71.82%	~69.6%	~73.0%	~74.5%

Code Generation — MBPP (3-shot, pass@1)

Model	Params	MBPP pass@1
Mamba / Mamba-2	370M	<10.0%
TinyLlama	1.1B	~19.91%
Kai-0.35B-Instruct	360M	22.20%
Llama-3.2-1B (Base)	1.0B	~25-30%
Llama-3.2-1B-Instruct	1.0B	~49.0%

Key Observations

ARC-Challenge: Kai-0.35B scores 37.80% (5-shot), significantly outperforming both Mamba-370M (+8.7pp) and TinyLlama-1.1B (+7.7pp) — a model 3x its size.
PIQA: At 71.82%, Kai-0.35B nearly matches TinyLlama-1.1B (73.0%) with only 1/3 the parameters, and trails the 1B-class Llama-3.2 by less than 3pp.
MBPP: At 22.20% pass@1, Kai-0.35B surpasses TinyLlama-1.1B (~19.91%) in code generation despite being 3x smaller.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained(
    "NoesisLab/Kai-0.35B-Instruct",
    torch_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained("NoesisLab/Kai-0.35B-Instruct")
messages = [{"role": "user", "content": "What is 25 * 4?"}]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt")
output = model.generate(input_ids, max_new_tokens=256)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Citation

@misc{noesislab2026nkai,
  title={Kai-0.35B-Instruct},
  author={NoesisLab},
  year={2026},
  url={https://huggingface.co/NoesisLab/Kai-0.35B-Instruct}
}

License

Apache 2.0

Downloads last month: 52

GGUF

Model size

0.4B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF

Base model

NoesisLab/Kai-0.35B-Instruct

Quantized

(2)

this model

Collection including Flexan/NoesisLab-Kai-0.35B-Instruct-GGUF

Community GGUFs

Collection

This collection contains quantized GGUF files for community models that did not have GGUF equivalents available yet. I do not own these models. • 58 items • Updated Apr 16

Evaluation results

Accuracy (normalized) on ARC-Challenge
test set self-reported

37.800
Accuracy (normalized) on HellaSwag
validation set self-reported

55.880
Accuracy (normalized) on PIQA
validation set self-reported

71.820
pass@1 on MBPP
test set self-reported

22.200