Instructions to use tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF 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 tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

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 tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
./llama-cli -hf tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

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 tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

Use Docker

docker model run hf.co/tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

LM Studio
Jan

vLLM

How to use tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tahaalam2009/VeriLoop-E2-GSQ-RCO-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": "tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

Ollama
How to use tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF with Ollama:
```
ollama run hf.co/tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S
```
Unsloth Desktop

How to use tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

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": "tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF with Docker Model Runner:
```
docker model run hf.co/tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S
```

Lemonade

How to use tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

Run and chat with the model

lemonade run user.VeriLoop-E2-GSQ-RCO-GGUF-IQ2_S

List all available models

lemonade list

Hermes Agent

How to use tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

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 tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S

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 "tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF:IQ2_S" \
  --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"

VeriLoop-E2-GSQ-RCO-GGUF / README.md

tahaalam2009

Upload README.md with huggingface_hub

5be47b2 verified 18 days ago

preview code

Raw History Blame

4.06 kB

metadata

base_model: tsinghua-sigs-robot-lab/VeriLoop-E2
base_model_relation: quantized
library_name: gguf
license: apache-2.0
tags:
  - gguf
  - gsq
  - rco
  - quantization
  - mixed-precision
  - veriloop
  - robotics
  - code
  - math

VeriLoop-E2 · GSQ-RCO Mixed-Precision GGUF (IQ3_XXS)

Community reproduction of a GSQ-RCO-style mixed-precision GGUF quantization of tsinghua-sigs-robot-lab/VeriLoop-E2.

Methodology Note: This model reuses the per-tensor precision allocation found by ISTA-DASLab's Riemannian Constrained Optimization (RCO) search for the base architecture (ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF), quantized against VeriLoop-E2's weights using llama.cpp (b11200) and a fresh importance matrix computed directly on VeriLoop-E2 with domain-matched code, math, and physics traces. This is a community reproduction applying ISTA-DASLab's allocation map, not an official ISTA-DASLab run (as RCO's search code is not yet publicly released).

Model Specifications

Parameter	Specification
Parent Model	`tsinghua-sigs-robot-lab/VeriLoop-E2`
Base Model Architecture	Qwen3.8-27B dense
Target BPW	3.00 (Measured: 3.03 BPW)
Quantized File Size	10.20 GB (10,196,595,264 bytes / 9.50 GiB)
BF16 Reference Size	53.81 GB (53,808,284,000 bytes / 50.11 GiB)
Size Reduction	81.05% smaller than BF16 (5.28x compression)
Total Tensors	851 (100% exact match to RCO allocation map)
Importance Matrix	Fresh imatrix generated on VeriLoop-E2 (30 chunks / 15,360 tokens of math, code, physics)

Benchmark & Fidelity Results (vs Canonical BF16 Reference)

Evaluations performed with llama-perplexity with context length 2048, batch 512, micro-batch 512, seed 42.

1. WikiText-2 Test (8 chunks, 16,384 tokens)

Model Tier	File Size	Effective BPW	Mean PPL	PPL Ratio	Mean KLD	Same Top-P	RMS Δp
BF16 Reference	50.11 GiB	16.00	4.8382 ± 0.1198	1.0000	0.0000	100.0%	0.0%
GSQ-RCO IQ3_XXS	9.50 GiB (10.20 GB)	3.03	5.2659 ± 0.1353	1.0884 ± 0.0066	0.1140 ± 0.0039	87.39 ± 0.37%	10.23 ± 0.27%

(Note: Baseline BF16 PPL of 4.8382 matches Tsinghua's published reference of 4.8404 within reported uncertainty).

2. Domain-Matched Code & Math Evaluation (4 chunks, 8,192 tokens)

Evaluated on held-out math reasoning traces (GSM8K test split) and Python programming (OpenAI HumanEval):

Model Tier	Effective BPW	Mean PPL	PPL Ratio	Mean KLD	Same Top-P	RMS Δp
BF16 Reference	16.00	1.9554 ± 0.0484	1.0000	0.0000	100.0%	0.0%
GSQ-RCO IQ3_XXS	3.03	2.1370 ± 0.0564	1.0929 ± 0.0109	0.1148 ± 0.0054	90.89 ± 0.45%	13.05 ± 0.43%

Notice that on domain code and math, Same Top-P agreement reaches 90.89% and PPL remains tight at 2.14 vs 1.96!

Included Artifacts

VeriLoop-E2-GSQ-RCO-IQ3_XXS.gguf: The mixed-precision 3.03 BPW model.
veriloop-e2.imatrix: The fresh importance matrix calculated on VeriLoop-E2.
tensor_types.txt: The exact per-tensor quant-type allocation applied to all 851 tensors.
eval_summary.json: Complete machine-readable benchmark records.

Usage with llama.cpp

# Download
huggingface-cli download tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF VeriLoop-E2-GSQ-RCO-IQ3_XXS.gguf --local-dir .

# Run inference
llama-cli -m VeriLoop-E2-GSQ-RCO-IQ3_XXS.gguf -p "Explain closed-loop robot trajectory optimization." -ngl 99

Citation & References

VeriLoop-E2: tsinghua-sigs-robot-lab/VeriLoop-E2
GSQ Paper: arXiv:2604.18556
RCO Paper: arXiv:2605.00649
Reference Base Allocation: ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF