Instructions to use tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-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 tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-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 tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL
# Run inference directly in the terminal:
llama cli -hf tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL
# Run inference directly in the terminal:
llama cli -hf tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

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 tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL
# Run inference directly in the terminal:
./llama-cli -hf tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

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 tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

Use Docker

docker model run hf.co/tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

LM Studio
Jan

vLLM

How to use tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-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": "tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-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/tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

Ollama
How to use tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF with Ollama:
```
ollama run hf.co/tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL
```
Unsloth Desktop

How to use tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

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": "tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF with Docker Model Runner:
```
docker model run hf.co/tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL
```

Lemonade

How to use tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

Run and chat with the model

lemonade run user.Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF-IQ3_S_XL

List all available models

lemonade list

Hermes Agent

How to use tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-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 tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

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 tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL

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 "tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF:IQ3_S_XL" \
  --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"

Qwen3.8-27B-GSQ-RCO — BuffedMod GGUF

This repository contains modified versions of the Qwen3.8-27B-GSQ-RCO-IQ3_S GGUF model.

Unlike traditional re-quantization workflows which require quantizing the entire model from unquantized FP16/BF16 weights, these files were created by directly modifying specific tensor weights within the binary GGUF file.

By replacing critical layer tensors (specifically output.weight) with higher-precision quantizations, we achieve better Perplexity (PPL), lower KL Divergence (KLD), and increased top-token agreement while maintaining a compact footprint.

⚡ What Changed in BuffedMod?

In lower-bit quantizations like IQ3_S, the output.weight tensor (LM Head) often serves as a major bottleneck for final text generation precision. Upgrading this tensor improves top-token probability matching without adding massive overhead to the overall file size.

📦 Available Variants

Qwen3.8-27B-GSQ-RCO-BuffedMod-IQ3_S_XL-mtp-Q6K.gguf
- Modifications: Replaced output.weight from Q4_K to Q6_K.
- Target: Maximum quality retention for IQ3_S baseline.
Qwen3.8-27B-GSQ-RCO-BuffedMod-IQ3_S_XL-mtp-IQ4XS.gguf
- Modifications: Replaced output.weight from Q4_K to Q6_K AND down-quantized MTP (Multi-Token Prediction) tensors from Q6_K to IQ4_XS.
- Target: Optimized size-to-performance balance by reclaiming memory from non-essential auxiliary tensors.

📊 Benchmark & Evaluation Results

All variants were evaluated using llama-perplexity with original BF16 base model (q38f16baseline.kld) to measure Perplexity (PPL) degradation, KL Divergence (KLD), and Token Probability shifts.

llama-perplexity.exe -f /wikitext-2-raw/wiki.test.raw \
    --kl-divergence \
    --kl-divergence-base q38f16baseline.kld \
    -ngl 99 \
    -m <model_variant>.gguf

📈 Comparison Summary

Metric	Original (`IQ3_S`)	BuffedMod (`Q6_K` Output)	Improvement
Mean PPL(Q)	`7.062697`	`7.032142`	🟢 -0.030555 (Lower is better)
Mean PPL Diff vs Base	`0.112205`	`0.081650`	🟢 -27.2% Error Reduction
Mean KLD	`0.055475`	`0.051738`	🟢 -6.7% Divergence
Median KLD	`0.022928`	`0.018899`	🟢 -17.5% Divergence
Same Top Token Probability	`89.657%`	`90.535%`	🟢 +0.878% Match
RMS Δp	`6.537%`	`6.285%`	🟢 -0.252% Variance

📐 Model Variant Comparison

The table below highlights the trade-off between file size efficiency and accuracy gains across the original and BuffedMod variants:

Model Variant	File Size	PPL(Q) ↓	PPL Diff vs Base ↓	Mean KLD ↓	Median KLD ↓	Top-Token Match ↑
Original (`IQ3_S-mtp`)	11.29 GB	7.0627	0.1122	0.0555	0.0229	89.66%
BuffedMod (`IQ4XS MTP`)	11.49 GB	7.0321	0.0817	0.0517	0.0189	90.54%
BuffedMod (`Q6_K MTP`)	11.59 GB	7.0321	0.0817	0.0517	0.0189	90.54%

📌 Key Highlights:

BuffedMod (IQ4XS MTP) offers the optimal sweet spot: it gains the full accuracy boost (+0.88% top-token match, -27.2% PPL error vs base) with only +200 MB size overhead compared to the original file.

BuffedMod (Q6_K MTP) retains maximum fidelity on the auxiliary MTP tensors for an extra +100 MB, maintaining identical core perplexity and divergence performance.

📋 Full Metrics Breakdown

🔴 Baseline Original Metrics (`IQ3_S` with `Q4_K` output.weight)

====== Perplexity statistics ======
Mean PPL(Q)                   :   7.062697 ±   0.045484
Mean PPL(base)                :   6.950493 ±   0.044934
Cor(ln(PPL(Q)), ln(PPL(base))):  98.65%
Mean ln(PPL(Q)/PPL(base))     :   0.016014 ±   0.001059
Mean PPL(Q)/PPL(base)         :   1.016143 ±   0.001076
Mean PPL(Q)-PPL(base)         :   0.112205 ±   0.007438

====== KL divergence statistics ======
Mean    KLD:   0.055475 ±   0.000453
Maximum KLD:  15.811345
99.9%   KLD:   2.067696
99.0%   KLD:   0.593792
95.0%   KLD:   0.188752
90.0%   KLD:   0.110145
Median  KLD:   0.022928

====== Token probability statistics ======
Mean    Δp: -0.513 ± 0.017 %
RMS Δp    :  6.537 ± 0.051 %
Same top p: 89.657 ± 0.079 %

🟢 BuffedMod Metrics (`IQ3_S` with `Q6_K` output.weight)

====== Perplexity statistics ======
Mean PPL(Q)                   :   7.032142 ±   0.045271
Mean PPL(base)                :   6.950493 ±   0.044934
Cor(ln(PPL(Q)), ln(PPL(base))):  98.72%
Mean ln(PPL(Q)/PPL(base))     :   0.011679 ±   0.001034
Mean PPL(Q)/PPL(base)         :   1.011747 ±   0.001046
Mean PPL(Q)-PPL(base)         :   0.081650 ±   0.007236

====== KL divergence statistics ======
Mean    KLD:   0.051738 ±   0.000450
Maximum KLD:  15.754954
99.9%   KLD:   2.056773
99.0%   KLD:   0.586696
95.0%   KLD:   0.181908
90.0%   KLD:   0.103020
Median  KLD:   0.018899

====== Token probability statistics ======
Mean    Δp: -0.477 ± 0.016 %
RMS Δp    :  6.285 ± 0.052 %
Same top p: 90.535 ± 0.076 %

📜 Credits & Acknowledgments

Original Model: ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
Modification: Tweak & Direct Tensor Modification by tooltd

Downloads last month: 1,004

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

3-bit

Model tree for tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF

Base model

Qwen/Qwen3.8-27B

Quantized

(1183)

this model

Qwen3.8-27B-GSQ-RCO — BuffedMod GGUF

⚡ What Changed in BuffedMod?

📦 Available Variants

📊 Benchmark & Evaluation Results

📈 Comparison Summary

📐 Model Variant Comparison

📋 Full Metrics Breakdown

🔴 Baseline Original Metrics (IQ3_S with Q4_K output.weight)

🟢 BuffedMod Metrics (IQ3_S with Q6_K output.weight)

📜 Credits & Acknowledgments

Model tree for tooltd/Qwen3.8-27B-GSQ-RCO-BuffedMod-GGUF

🔴 Baseline Original Metrics (`IQ3_S` with `Q4_K` output.weight)

🟢 BuffedMod Metrics (`IQ3_S` with `Q6_K` output.weight)