Instructions to use Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-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 Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-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 Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_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 Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_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 Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF with Ollama:
```
ollama run hf.co/Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_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": "Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M
```

Lemonade

How to use Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-27B-GLM5.1-Distill-v1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-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 Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_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 Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_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 "Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Q4_K_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"

Fredred89 commited on Jun 6

Commit

592d782

verified ·

1 Parent(s): 83a32f9

Upload PREDATOR_4A_4BIT_CHAMPION_README.md with huggingface_hub

Browse files

Files changed (1) hide show

PREDATOR_4A_4BIT_CHAMPION_README.md +18 -0

PREDATOR_4A_4BIT_CHAMPION_README.md ADDED Viewed

	@@ -0,0 +1,18 @@

+# Qwen3.5-27B-GLM5.1-Distill-v1-4A-4BIT-CHAMPION
+**New Predator champion (2026-06-05).** Beats 4A BEST by 0.0056 PPL (chunks=30, Z=22.0, p<1e-19, 30/30 chunks improved).
+## Result
+- PPL chunks=30: 6.2342 (was 6.2398 for 4A BEST on original F16)
+- File size: 16.98 GB (SAME as 4A BEST)
+- Same tensor-type-file as 4A BEST
+- Different weights (rotated by Chrysalis calibrated for 4-bit)
+## How
+- Pre-rotated F16 with Chrysalis butterflies calibrated for 4-bit quantization loss (not 2-bit)
+- Quantized with PREDATOR_4A_BEST.tensor_types.quant.txt
+- 544 matrices × 50 SGD steps × 2.5 min/layer = 158.8 min on VSI 2x L40S
+## See also
+- 4A BEST (the previous champion, beats Q4_K_M by 0.0369 PPL): Fredred89/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF
+- Methodology: 4-bit Chrysalis calibration finds gentler rotations than 2-bit; at 4-bit they HELP (small but real)