Instructions to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF",
	filename="Qwen2.5-Coder-32B-Instruct-bf16-00001-of-00003.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

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 CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

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 CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

Use Docker

docker model run hf.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

LM Studio
Jan

vLLM

How to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-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": "CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

Ollama
How to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF with Ollama:
```
ollama run hf.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16
```

Unsloth Studio

How to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-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 CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-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 CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF to start chatting

How to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

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 CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

Run Hermes

hermes

Docker Model Runner
How to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF with Docker Model Runner:
```
docker model run hf.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16
```

Lemonade

How to use CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF:BF16

Run and chat with the model

lemonade run user.Qwen2.5-Coder-32B-Instruct-SOTA-GGUF-BF16

List all available models

lemonade list

CISCai commited on Jan 6, 2025

Commit

b60ff27

verified ·

1 Parent(s): 1142221

Added links to full context YaRN-enabled GGUFs

Browse files

Files changed (1) hide show

README.md +13 -11

README.md CHANGED Viewed

@@ -33,6 +33,8 @@ Quantization was done with an importance matrix that was trained for ~1M tokens
 Fill-in-Middle tokens are automatically detected and supported as of commit [11ac980](https://github.com/ggerganov/llama.cpp/commit/11ac9800aff532715a5bc7991062c68ba3472e6e), see [example](#simple-llama-cpp-python-example-fill-in-middle-code).
 <!-- description end -->
@@ -86,17 +88,17 @@ Refer to the Provided Files table below to see what files use which methods, and
 | Name | Quant method | Bits | Size | Max RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-| [Qwen2.5-Coder-32B-Instruct.IQ1_S.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ1_S.gguf) | IQ1_S | 1 | 6.8 GB| 7.8 GB | smallest, significant quality loss |
-| [Qwen2.5-Coder-32B-Instruct.IQ1_M.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ1_M.gguf) | IQ1_M | 1 | 7.4 GB| 8.4 GB | very small, significant quality loss |
-| [Qwen2.5-Coder-32B-Instruct.IQ2_XXS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ2_XXS.gguf) | IQ2_XXS | 2 | 8.4 GB| 9.4 GB | very small, high quality loss |
-| [Qwen2.5-Coder-32B-Instruct.IQ2_XS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ2_XS.gguf) | IQ2_XS | 2 | 9.3 GB| 10.3 GB | very small, high quality loss |
-| [Qwen2.5-Coder-32B-Instruct.IQ2_S.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ2_S.gguf) | IQ2_S | 2 | 9.7 GB| 10.7 GB | small, substantial quality loss |
-| [Qwen2.5-Coder-32B-Instruct.IQ2_M.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ2_M.gguf) | IQ2_M | 2 | 10.5 GB| 11.5 GB | small, greater quality loss |
-| [Qwen2.5-Coder-32B-Instruct.IQ3_XXS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ3_XXS.gguf) | IQ3_XXS | 3 | 11.9 GB| 12.9 GB | very small, high quality loss |
-| [Qwen2.5-Coder-32B-Instruct.IQ3_XS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ3_XS.gguf) | IQ3_XS | 3 | 12.8 GB| 13.8 GB | small, substantial quality loss |
-| [Qwen2.5-Coder-32B-Instruct.IQ3_S.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ3_S.gguf) | IQ3_S | 3 | 13.4 GB| 14.4 GB | small, greater quality loss |
-| [Qwen2.5-Coder-32B-Instruct.IQ3_M.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ3_M.gguf) | IQ3_M | 3 | 13.8 GB| 14.8 GB | medium, balanced quality - recommended |
-| [Qwen2.5-Coder-32B-Instruct.IQ4_XS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4 | 16.5 GB| 17.5 GB | small, substantial quality loss |
 Generated importance matrix file: [Qwen2.5-Coder-32B-Instruct.imatrix.dat](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.imatrix.dat)

 Fill-in-Middle tokens are automatically detected and supported as of commit [11ac980](https://github.com/ggerganov/llama.cpp/commit/11ac9800aff532715a5bc7991062c68ba3472e6e), see [example](#simple-llama-cpp-python-example-fill-in-middle-code).
+**Update January 6th 2025**: Added links to full context YaRN-enabled GGUFs (using [GGUF Editor](https://huggingface.co/spaces/CISCai/gguf-editor)).
 <!-- description end -->
 | Name | Quant method | Bits | Size | Max RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
+| [Qwen2.5-Coder-32B-Instruct.IQ1_S.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ1_S.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ1_S.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ1_S | 1 | 6.8 GB| 7.8 GB | smallest, significant quality loss |
+| [Qwen2.5-Coder-32B-Instruct.IQ1_M.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ1_M.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ1_M.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ1_M | 1 | 7.4 GB| 8.4 GB | very small, significant quality loss |
+| [Qwen2.5-Coder-32B-Instruct.IQ2_XXS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ2_XXS.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ2_XXS.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ2_XXS | 2 | 8.4 GB| 9.4 GB | very small, high quality loss |
+| [Qwen2.5-Coder-32B-Instruct.IQ2_XS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ2_XS.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ2_XS.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ2_XS | 2 | 9.3 GB| 10.3 GB | very small, high quality loss |
+| [Qwen2.5-Coder-32B-Instruct.IQ2_S.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ2_S.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ2_S.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ2_S | 2 | 9.7 GB| 10.7 GB | small, substantial quality loss |
+| [Qwen2.5-Coder-32B-Instruct.IQ2_M.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ2_M.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ2_M.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ2_M | 2 | 10.5 GB| 11.5 GB | small, greater quality loss |
+| [Qwen2.5-Coder-32B-Instruct.IQ3_XXS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ3_XXS.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ3_XXS.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ3_XXS | 3 | 11.9 GB| 12.9 GB | very small, high quality loss |
+| [Qwen2.5-Coder-32B-Instruct.IQ3_XS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ3_XS.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ3_XS.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ3_XS | 3 | 12.8 GB| 13.8 GB | small, substantial quality loss |
+| [Qwen2.5-Coder-32B-Instruct.IQ3_S.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ3_S.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ3_S.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ3_S | 3 | 13.4 GB| 14.4 GB | small, greater quality loss |
+| [Qwen2.5-Coder-32B-Instruct.IQ3_M.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ3_M.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ3_M.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ3_M | 3 | 13.8 GB| 14.8 GB | medium, balanced quality - recommended |
+| [Qwen2.5-Coder-32B-Instruct.IQ4_XS.gguf](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.IQ4_XS.gguf) ([with YaRN](https://ciscai-gguf-editor.hf.space/download/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/Qwen2.5-Coder-32B-Instruct.IQ4_XS.gguf?branch=main&add=%5B%22qwen2.context_length%22,4,131072%5D&add=%5B%22qwen2.rope.scaling.type%22,8,%22yarn%22%5D&add=%5B%22qwen2.rope.scaling.factor%22,6,4%5D&add=%5B%22qwen2.rope.scaling.original_context_length%22,4,32768%5D)) | IQ4_XS | 4 | 16.5 GB| 17.5 GB | small, substantial quality loss |
 Generated importance matrix file: [Qwen2.5-Coder-32B-Instruct.imatrix.dat](https://huggingface.co/CISCai/Qwen2.5-Coder-32B-Instruct-SOTA-GGUF/blob/main/Qwen2.5-Coder-32B-Instruct.imatrix.dat)