Instructions to use Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF", dtype="auto")

llama-cpp-python

How to use Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF",
	filename="aquif-3.6-1b-q4_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Edge-Quant/aquif-3.6-1B-Q4_K_M-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 Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Edge-Quant/aquif-3.6-1B-Q4_K_M-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 Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Edge-Quant/aquif-3.6-1B-Q4_K_M-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 Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M

SGLang

How to use Edge-Quant/aquif-3.6-1B-Q4_K_M-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 "Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use Edge-Quant/aquif-3.6-1B-Q4_K_M-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 Edge-Quant/aquif-3.6-1B-Q4_K_M-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 Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF to start chatting

Docker Model Runner
How to use Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.aquif-3.6-1B-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

aquif-3.6-1B-Q4_K_M-GGUF / README.md

Edge-Quant

Update README.md

634dbdd verified 6 months ago

preview code

raw

history blame contribute delete

4.95 kB

metadata

license: apache-2.0
base_model: aquif-ai/aquif-3.6-1B
tags:
  - text-generation-inference
  - reasoning
  - thinking
  - hybrid
  - efficient
  - dynamic
  - transformers
  - aquif
  - math
  - coding
  - small
  - aquif-3.5
  - aquif-3.6
  - llm
  - llama-cpp
  - gguf-my-repo
language:
  - en
  - de
  - it
  - pt
  - fr
  - hi
  - es
  - th
  - zh
  - ja
library_name: transformers
pipeline_tag: text-generation

aquif-3.6-1B

Summary

aquif-3.6-1B is a hybrid reasoning model that automatically determines when and how deeply to think based on query complexity. Built on aquif-3.5-Nano-1B with AutoThink RL data, it achieves 28% better token efficiency and 4% performance improvement across benchmarks.

Key Features - Dynamic reasoning, efficiency gains, and smart resource allocation
Performance - Benchmark results showing 4% average improvement
Token Efficiency - 28% reduction in token usage
Thinking Ratio - 12% reduction in thinking frequency
Benchmark Highlights - Detailed results for AIME, LiveCodeBench, and GPQA Diamond
Model Details - Architecture and specifications
Usage - Code examples for implementation
Previous Versions - Links to earlier models

Automatic Thinking

aquif-3.6-1B is a hybrid reasoning model that dynamically decides if and how much to think based on query complexity. Inspired by aquif-3.6-8B's approach of automatic thinking using AutoThink RL data on top of aquif-3.5-Nano-1B, the model uses the following format:

<judge>
[analyzes whether to think or not]
</judge>

<think_on/off>
<think>
[thinking content]
</think>

<answer>
</answer>

This is the same format as aquif-3.6-8B. Unlike something like aquif-3.5-Plus's toggleable reasoning that requires manual control (thinking_on/off), aquif-3.6's judge autonomously allocates reasoning depth - intelligently adapting its cognitive effort to each task automatically.

Key Features

🧠 Dynamic Reasoning: Automatically determines when and how deeply to think
⚡ 28% More Efficient: Significant token reduction while improving performance
📈 Better Performance: 4% average improvement across benchmarks
🎯 Smart Resource Allocation: 12% reduction in thinking ratio on average

Performance

Benchmark	aquif-3.6-1B	Qwen3-1.7B	Improvement
AIME 2025	75.0	39.4	+35.6%
LiveCodeBench	57.5	33.2	+24.3%
GPQA Diamond	52.8	40.1	+12.7%
Average	61.8	37.6	+24.2%

Token Efficiency

Benchmark	aquif-3.6-1B	Qwen3-1.7B	Reduction
AIME 2025	13,670	18,450	-26%
LiveCodeBench	10,270	13,890	-26%
GPQA Diamond	6,870	12,100	-43%
Average	10,270	14,813	-32%

Thinking Ratio

Benchmark	aquif-3.6-1B	Qwen3-1.7B	Reduction
AIME 2025	84.0%	100.0%	-16%
LiveCodeBench	78.0%	100.0%	-22%
GPQA Diamond	81.0%	100.0%	-19%
Average	81.0%	100.0%	-19%

Benchmark Highlights

AIME 2025: 26% fewer tokens, +35.6% performance, -16% thinking ratio
LiveCodeBench: 26% fewer tokens, +24.3% performance, -22% thinking ratio
GPQA Diamond: 43% fewer tokens, +12.7% performance, -19% thinking ratio

Model Details

Base Model: 1.7B parameters
Architecture: Hybrid reasoning with dynamic thinking allocation
Context Length: 40K tokens
License: Apache 2.0

Usage

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF --hf-file aquif-3.6-1b-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF --hf-file aquif-3.6-1b-q4_k_m.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF --hf-file aquif-3.6-1b-q4_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo Edge-Quant/aquif-3.6-1B-Q4_K_M-GGUF --hf-file aquif-3.6-1b-q4_k_m.gguf -c 2048

Edge-Quant
/

aquif-3.6-1B-Q4_K_M-GGUF