Instructions to use MarxistLeninist/Qwen3.8-27B-IQ1_M-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 MarxistLeninist/Qwen3.8-27B-IQ1_M-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 MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_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 MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_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 MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M

Use Docker

docker model run hf.co/MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M

LM Studio
Jan

vLLM

How to use MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MarxistLeninist/Qwen3.8-27B-IQ1_M-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": "MarxistLeninist/Qwen3.8-27B-IQ1_M-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/MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M

Ollama
How to use MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF with Ollama:
```
ollama run hf.co/MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M
```
Unsloth Desktop

How to use MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M

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": "MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF with Docker Model Runner:
```
docker model run hf.co/MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M
```

Lemonade

How to use MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-IQ1_M-GGUF-IQ1_M

List all available models

lemonade list

Hermes Agent

How to use MarxistLeninist/Qwen3.8-27B-IQ1_M-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 MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M

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 MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M

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 "MarxistLeninist/Qwen3.8-27B-IQ1_M-GGUF:IQ1_M" \
  --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-IQ1_M-GGUF / AGENTIC_VALIDATION /RUN_AGENTIC_ADAPTER.sh

MarxistLeninist

Add repaired IQ1_M agentic adapter and 6-of-6 validation

b89269a verified 25 days ago

Raw

History Blame Contribute Delete

2.51 kB

	#!/usr/bin/env bash
	set -Eeuo pipefail

	HERE=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)
	REPO_ROOT=$(cd -- "$HERE/.." && pwd)
	MODEL=${MODEL:-"$REPO_ROOT/Qwen3.8-27B-IQ1_M.gguf"}
	LLAMA_SERVER=${LLAMA_SERVER:-llama-server}
	LLAMA_HOST=${LLAMA_HOST:-127.0.0.1}
	LLAMA_PORT=${LLAMA_PORT:-18539}
	ADAPTER_HOST=${ADAPTER_HOST:-127.0.0.1}
	ADAPTER_PORT=${ADAPTER_PORT:-18540}
	THREADS=${THREADS:-16}
	CTX_SIZE=${CTX_SIZE:-1024}
	LOG_DIR=${LOG_DIR:-"$HERE/runtime-logs"}

	mkdir -p "$LOG_DIR"
	[[ -f "$MODEL" ]] \|\| { echo "Model not found: $MODEL" >&2; exit 2; }
	command -v "$LLAMA_SERVER" >/dev/null 2>&1 \|\| { echo "llama-server not found: $LLAMA_SERVER" >&2; exit 3; }
	command -v python3 >/dev/null 2>&1 \|\| { echo "python3 is required" >&2; exit 4; }

	cleanup() {
	local rc=$?
	[[ -n "${ADAPTER_PID:-}" ]] && kill -TERM "$ADAPTER_PID" 2>/dev/null \|\| true
	[[ -n "${LLAMA_PID:-}" ]] && kill -TERM "$LLAMA_PID" 2>/dev/null \|\| true
	wait "${ADAPTER_PID:-}" 2>/dev/null \|\| true
	wait "${LLAMA_PID:-}" 2>/dev/null \|\| true
	exit "$rc"
	}
	trap cleanup EXIT INT TERM

	"$LLAMA_SERVER" \
	--model "$MODEL" \
	--alias Qwen3.8-27B-IQ1_M-agentic \
	--host "$LLAMA_HOST" \
	--port "$LLAMA_PORT" \
	--threads "$THREADS" \
	--threads-batch "$THREADS" \
	--ctx-size "$CTX_SIZE" \
	--batch-size 512 \
	--ubatch-size 128 \
	--parallel 1 \
	--cache-type-k q4_0 \
	--cache-type-v q4_0 \
	--jinja \
	--reasoning off \
	--reasoning-budget 0 \
	--no-mmproj \
	--cache-ram 0 \
	--ctx-checkpoints 0 \
	--no-warmup \
	>"$LOG_DIR/llama-server.log" 2>&1 &
	LLAMA_PID=$!

	for _ in $(seq 1 600); do
	if curl -fsS --max-time 2 "http://$LLAMA_HOST:$LLAMA_PORT/health" >/dev/null 2>&1; then
	break
	fi
	kill -0 "$LLAMA_PID" 2>/dev/null \|\| { tail -100 "$LOG_DIR/llama-server.log" >&2; exit 5; }
	sleep 1
	done
	curl -fsS --max-time 2 "http://$LLAMA_HOST:$LLAMA_PORT/health" >/dev/null

	python3 -u "$HERE/ADAPTER.py" \
	--host "$ADAPTER_HOST" \
	--port "$ADAPTER_PORT" \
	--upstream "http://$LLAMA_HOST:$LLAMA_PORT" \
	>"$LOG_DIR/adapter.log" 2>&1 &
	ADAPTER_PID=$!

	for _ in $(seq 1 60); do
	if curl -fsS --max-time 2 "http://$ADAPTER_HOST:$ADAPTER_PORT/health" >/dev/null 2>&1; then
	break
	fi
	kill -0 "$ADAPTER_PID" 2>/dev/null \|\| { tail -100 "$LOG_DIR/adapter.log" >&2; exit 6; }
	sleep 1
	done
	curl -fsS --max-time 2 "http://$ADAPTER_HOST:$ADAPTER_PORT/health" >/dev/null

	echo "Agentic OpenAI-compatible endpoint: http://$ADAPTER_HOST:$ADAPTER_PORT/v1/chat/completions"
	echo "Logs: $LOG_DIR"
	wait "$ADAPTER_PID"