Instructions to use ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
./llama-cli -hf ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S

Use Docker

docker model run hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S

Llama new
LM Studio
Jan

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/Qwen3.8-27B-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": "ISTA-DASLab/Qwen3.8-27B-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/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S

Ollama
How to use ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF with Ollama:
```
ollama run hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
```
Unsloth Desktop

How to use ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-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": "ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S

Run and chat with the model

lemonade run user.Qwen3.8-27B-GSQ-RCO-GGUF-IQ2_S

List all available models

lemonade list

Hermes Agent

How to use ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-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 "ISTA-DASLab/Qwen3.8-27B-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"

New discussion

Resources

View closed (7)

Methodological feedback on "full model performance" claims: Need for control quants (Q6/Q8) and Jinja/eval transparency

#63 opened 1 day ago by

akierum

RTX 5060 Ti 16GB benchmarks + undervolt + memory overclock - Qwen3.8-27B-GSQ-RCO-IQ2_S

👍 2

#62 opened 1 day ago by

glrtdev

base64 decoding test on 150 chunks

#60 opened 5 days ago by

KottCh

Using IQ3_S-MTP on 9060XT(16) but got problems with overthinking

#59 opened 5 days ago by

HelloApplepie

Where would Ternary Bonsai 2 be positioned on the "Task average vs. bit width" chart from the model description?

#58 opened 10 days ago by

ssvb

The best, highest-quality quantization.

❤️🤝 7

#57 opened 17 days ago by

Kamil21322

Using this model with Continue in VSCode and Ollama (does not work)

#56 opened 18 days ago by

theHumanAT

Qwen3.5 9B GSQ-RCO?

👍 1

#55 opened 20 days ago by

olegshulyakov

GSQ-RCO for tsinghua-sigs-robot-lab/VeriLoop-E2 ?

#54 opened 20 days ago by

wukongai

Great model quality under heavy quantize

🚀 2

#53 opened 21 days ago by

mythrime

Why stopped at IQ3_S?

#52 opened 24 days ago by

charleswg

Gemma models GSQ RCO?

👍 5

#51 opened 26 days ago by

Mk2Oracle

Request: Qwen3.6-35B-A3B GSQ-RCO GGUF

👍 10

#50 opened 27 days ago by

Queennox

GSQ-RCO for ThinkingCap-Qwen3.8-27B?

🔥 6

#47 opened about 1 month ago by

Exo87

Have you seen DavidAU's work?

🧠👍 17

#46 opened about 1 month ago by

69crc

MiMo-V2.6-Flash-RL is a MONSTER. Please, make a GSK version

👍❤️ 6

#45 opened about 1 month ago by

Nerdsking

Request: ALU Optimized, Uniform / Linear 4-Bit (Q4_0)

#44 opened about 1 month ago by

Decep-Qi-Kons

Best GGUF quant for Qwen3.8-27B: quality vs file size

👀👍 10

#43 opened about 1 month ago by

yash-711

Share a method to run this model with 5060ti 16G @ 256k: 40+ tok/s

❤️👍 9

#42 opened about 1 month ago by

leyewang

Could you release an uncensored version?

➕👍 10

#41 opened about 1 month ago by

wuxingaef

5060 TI 16 gb VRAM 128k context

👍❤️ 3

#40 opened about 1 month ago by

adsanz

Just wanted to say "thanks" and works great now that I've tuned to my system

❤️👍 7

#39 opened about 1 month ago by

bluegorilla4192

Swift-Qwen3.8-27B-GGUF - is it possible to quantize this model?

🚀👍 17

#37 opened about 1 month ago by

GroBmeister

IQ3_S for 16 GB VRAM Users

🔥 1

#36 opened about 2 months ago by

baybobey

Template: resolved_reasoning_effort for `medium` is missing? XXS

#34 opened about 2 months ago by

bluegorilla4192

Better than similar quants, actually completes tasks

#33 opened about 2 months ago by

stonkersson

Miracle did not happen

#32 opened about 2 months ago by

ThaiCat

Interesting paper: free harness on Qwen3.8-27B vs Fable 5

👍 2

#31 opened about 2 months ago by

Abl1ttheworld

GSQ-RCO-GGUF

🚀 1

#30 opened about 2 months ago by

goodasdgood

Task effectiveness maintained – Knowledge loss expected

👍 1

#29 opened about 2 months ago by

fakezeta

how to use imatrix-qwen3.8-27b.gguf in llama.cpp

#27 opened about 2 months ago by

fryng

Works nicely on NVidia GeForce RTX 5080 (16 GB), thanks

#26 opened about 2 months ago by

VessAU

Tested it on ,,huge" coding project + hermes, well done guys! AMD 7900XTX <3

#25 opened about 2 months ago by

flitzfox

The words generated by the model will be misspelled

😔 1

#24 opened about 2 months ago by

houuse78

DFlash2

➕🚀 3

#23 opened about 2 months ago by

countofserenno

Is this model same as Q4KM for coding related tasks?

#22 opened about 2 months ago by

soyalemujica

run

👀 1

#21 opened about 2 months ago by

goodasdgood

This model is indeed smarter, thanks to the author's effort.

#20 opened about 2 months ago by

yw1816

This is amazing, now i have 250k ctx

🤗👍 3

#19 opened about 2 months ago by

47Hunter47

#Request: Would u consider moe gguf models at around 8-11gbs size with same quant and mtp overhead attached please?

#18 opened about 2 months ago by

ahmedsevenup

GGUF versions available via Torrent

👍 2

#17 opened about 2 months ago by

baiomys

inference speed on apple silicon

#16 opened about 2 months ago by

Chillzyg

Abliterated PLS!

🔥 6

#15 opened about 2 months ago by

Fndxxxx

Update metadata (general.type)

#14 opened about 2 months ago by

flex55p4

Update metadata (general.type)

#13 opened about 2 months ago by

flex55p4

Update metadata (general.type)

#12 opened about 2 months ago by

flex55p4

finyx

#11 opened about 2 months ago by

flex55p4

finyx

#10 opened about 2 months ago by

flex55p4

MLX version Please！

🚀 4

#9 opened about 2 months ago by

greenerdalii

Would you consider GSQ-RCO IQ3_S + MTP for a Qwen3.8-27B coding-focused fine-tune?

🚀 1

#8 opened about 2 months ago by

Schestex