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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="steampunque/Qwen2.5-Coder-32B-Instruct-MP-GGUF",
	filename="Qwen2.5-Coder-32B-Instruct.Q4_K_H.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

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

Install from brew

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

Install from WinGet (Windows)

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

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

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

Use Docker

docker model run hf.co/steampunque/Qwen2.5-Coder-32B-Instruct-MP-GGUF

LM Studio
Jan
Ollama
How to use steampunque/Qwen2.5-Coder-32B-Instruct-MP-GGUF with Ollama:
```
ollama run hf.co/steampunque/Qwen2.5-Coder-32B-Instruct-MP-GGUF
```

Unsloth Studio new

How to use steampunque/Qwen2.5-Coder-32B-Instruct-MP-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 steampunque/Qwen2.5-Coder-32B-Instruct-MP-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 steampunque/Qwen2.5-Coder-32B-Instruct-MP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

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

Start the llama.cpp server

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

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": "steampunque/Qwen2.5-Coder-32B-Instruct-MP-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use steampunque/Qwen2.5-Coder-32B-Instruct-MP-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 steampunque/Qwen2.5-Coder-32B-Instruct-MP-GGUF

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 steampunque/Qwen2.5-Coder-32B-Instruct-MP-GGUF

Run Hermes

hermes

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

Lemonade

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

Pull the model

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

Run and chat with the model

lemonade run user.Qwen2.5-Coder-32B-Instruct-MP-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Mixed Precision GGUF layer quantization of Qwen2.5-Coder-32B-Instruct by Qwen

Original model: https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct

The hybrid quant employs different quantization levels on a per layer basis to enable both high performance and small file size at the same time. The quants employed are all K to avoid slow CPU or older GPU processing of IQ quants.

Q4_K_H layer quants are as follows:

Q4_K_L : Q4_K_M + attn_o = q6_k
Q5_K_L : Q5_K_L : attn_v = q8_0 attn_o = q6_k ffn_d = q6_k
Q6_K_S : Q6_K

   LAYER_TYPES='[
   [0 ,"Q5_K_L"],[1 ,"Q5_K_M"],[2 ,"Q5_K_S"],[3 ,"Q4_K_L"],[4 ,"Q4_K_M"],[5 ,"Q4_K_S"],[6 ,"Q3_K_L"],[7 ,"Q3_K_M"],
   [8 ,"Q3_K_L"],[9 ,"Q3_K_M"],[10,"Q3_K_L"],[11,"Q3_K_M"],[12,"Q3_K_L"],[13,"Q3_K_M"],[14,"Q3_K_L"],[15,"Q3_K_M"],
   [16,"Q3_K_L"],[17,"Q3_K_L"],[18,"Q3_K_L"],[19,"Q3_K_L"],[20,"Q3_K_L"],[21,"Q3_K_L"],[22,"Q3_K_L"],[23,"Q3_K_L"],
   [24,"Q4_K_S"],[25,"Q3_K_L"],[26,"Q4_K_S"],[27,"Q3_K_L"],[28,"Q4_K_S"],[29,"Q3_K_L"],[30,"Q4_K_S"],[31,"Q3_K_L"],
   [32,"Q4_K_S"],[33,"Q4_K_S"],[34,"Q4_K_S"],[35,"Q4_K_S"],[36,"Q4_K_S"],[37,"Q4_K_S"],[38,"Q4_K_S"],[39,"Q4_K_S"],
   [40,"Q4_K_M"],[41,"Q4_K_S"],[42,"Q4_K_M"],[43,"Q4_K_S"],[44,"Q4_K_M"],[45,"Q4_K_S"],[46,"Q4_K_M"],[47,"Q4_K_S"],
   [48,"Q4_K_M"],[49,"Q4_K_M"],[50,"Q4_K_M"],[51,"Q4_K_M"],[52,"Q4_K_M"],[53,"Q4_K_M"],[54,"Q4_K_M"],[55,"Q4_K_M"],
   [56,"Q4_K_M"],[57,"Q4_K_L"],[58,"Q4_K_M"],[59,"Q4_K_L"],[60,"Q5_K_S"],[61,"Q5_K_M"],[62,"Q5_K_L"],[63,"Q6_K_S"]
   ]'
   FLAGS="--token-embedding-type Q4_K --output-tensor-type Q6_K --layer-types-high"

This quant was optimized over a small set of curated test prompts for code generation ability and then sanity checked for good performance on humaneval.

Comparison:

Quant	size	PPL	Comment
IQ4_XS	17.9e9	7.5	-
Q4_K_H	19.4e9	7.5	Hybrid quant with Q4_K embedding Q6_K output

Usage:

The model can be speculated with Qwen 2.5 Coder 0.5B Instruct with no vocab translation. It is trained at 32k context which can be extended to 128k using YARN:

-rope-scaling yarn --yarn-orig-ctx 32768 --rope_scale 4

For other than 128k context set rope_scale to the fraction of configured context size / 32768.0.

Approximate performance on 2X 12G VRAM 4070 with RPC (1Gb/s local LAN), all weigths and context in VRAM:

Q	QKV	ND	NKV	gen tps	Comment
Q4_K_H	F16	0	15k	21	No draft
Q4_K_H	F16	12	12k	79	Spec 12
Q4_K_H	Q8_0	0	27k	21	No draft
Q4_K_H	Q8_0	12	21k	78	Spec 12

for speculation a fixed length ND=12 token draft was used with a custom downstream speculator. The test prompt is humaneval first problem:

generate python code for the described function header:

from typing import List

def has_close_elements(numbers: List[float], threshold: float) -> bool:
    """ Check if in given list of numbers, are any two numbers closer to each other than
    given threshold.
    >>> has_close_elements([1.0, 2.0, 3.0], 0.5)
    False
    >>> has_close_elements([1.0, 2.8, 3.0, 4.0, 5.0, 2.0], 0.3)
    True
    """

Benchmarks:

A full set of code evals for the quant is given here: https://huggingface.co/spaces/steampunque/benchlm