Instructions to use Davidmg0815/Qwen3.8-27B-MTP-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 Davidmg0815/Qwen3.8-27B-MTP-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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

Use Docker

docker model run hf.co/Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Davidmg0815/Qwen3.8-27B-MTP-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": "Davidmg0815/Qwen3.8-27B-MTP-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/Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

Ollama
How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with Ollama:
```
ollama run hf.co/Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
```

Unsloth Studio

How to use Davidmg0815/Qwen3.8-27B-MTP-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 Davidmg0815/Qwen3.8-27B-MTP-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 Davidmg0815/Qwen3.8-27B-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Davidmg0815/Qwen3.8-27B-MTP-GGUF to start chatting

How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

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": "Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
```

Lemonade

How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

Run and chat with the model

lemonade run user.Qwen3.8-27B-MTP-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Davidmg0815/Qwen3.8-27B-MTP-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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0

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 "Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0" \
  --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-MTP-GGUF

File size: 2,166 Bytes

c4bfc1e

#!/usr/bin/env bash
# Prueft, ob unser llama.cpp-Build von GitHub-Issue #24485 betroffen ist:
# quantisierter KV-Cache + Flash-Attention fallen ohne GGML_CUDA_FA_ALL_QUANTS
# STILL auf CPU-Attention zurueck. Symptom laut Issue: 25-45x langsamerer
# Prefill, GPU bei 0 Prozent, keine Warnung.
#
# Messgroesse ist die Prompt-Rate (prompt_per_second) bei einem langen Prompt —
# genau dort schlaegt der Unterschied durch, nicht bei der Token-Erzeugung.
set -uo pipefail

PREP=/mnt/models/qwen38-prep
BIN=/mnt/models/bin/llama-server
M=/mnt/models/PropellerA-models/qwen3.8-27b-Q8_0.gguf
PORT=8291
ERG=$PREP/fa-test
mkdir -p "$ERG"
echo $$ > "$PREP/.runner.pid"
trap 'rm -f "$PREP/.runner.pid"' EXIT

stop() {
for pid in $(pgrep -x llama-server 2>/dev/null); do kill -TERM "$pid" 2>/dev/null; done
for i in $(seq 1 25); do pgrep -x llama-server >/dev/null 2>&1 || break; sleep 1; done
for pid in $(pgrep -x llama-server 2>/dev/null); do kill -9 "$pid" 2>/dev/null; done
sleep 3
}

warte() {
for i in $(seq 1 200); do
curl -s -m 3 "http://127.0.0.1:$PORT/health" 2>/dev/null | grep -q ok && return 0
sleep 2
done
return 1
}

# $1 = Kurzname, $2/$3 = cache-type-k/v, $4 = flash-attn on|off
mess() {
local kurz="$1" ck="$2" cv="$3" fa="$4"
echo
echo "### $kurz  (KV $ck/$cv, flash-attn $fa)"
stop
nohup "$BIN" -m "$M" --host 127.0.0.1 --port "$PORT" \
--ctx-size 16384 --parallel 1 --n-gpu-layers 99 --tensor-split 1,1,1 \
--cache-type-k "$ck" --cache-type-v "$cv" --flash-attn "$fa" --jinja \
> "$ERG/server-$kurz.log" 2>&1 &
if ! warte; then
echo "  SERVER KAM NICHT HOCH"
grep -iE "error|failed|not supported|unsupported" "$ERG/server-$kurz.log" | tail -4
stop; return 1
fi
# Warnungen des Servers zu Flash-Attention festhalten.
grep -iE "flash|fattn|attention" "$ERG/server-$kurz.log" | tail -3 | sed 's/^/  LOG: /'

/mnt/models/skinnyJoe-venv/bin/python "$PREP/fa_probe.py" "$PORT" "$kurz" \
| tee -a "$ERG/ergebnis.txt"
stop
}

: > "$ERG/ergebnis.txt"
echo "=== Flash-Attention x quantisierter KV-Cache ==="
mess "q8_0-fa-on"  q8_0 q8_0 on
mess "f16-fa-on"   f16  f16  on
mess "q8_0-fa-off" q8_0 q8_0 off
echo
echo "=== Zusammenfassung ==="
cat "$ERG/ergebnis.txt"