Instructions to use steampunque/Qwen2.5-Coder-7B-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-7B-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-7B-Instruct-MP-GGUF",
	filename="Qwen2.5-Coder-7B-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-7B-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-7B-Instruct-MP-GGUF:Q6_K_H
# Run inference directly in the terminal:
llama-cli -hf steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF:Q6_K_H

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-7B-Instruct-MP-GGUF:Q6_K_H
# Run inference directly in the terminal:
llama-cli -hf steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF:Q6_K_H

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-7B-Instruct-MP-GGUF:Q6_K_H
# Run inference directly in the terminal:
./llama-cli -hf steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF:Q6_K_H

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-7B-Instruct-MP-GGUF:Q6_K_H
# Run inference directly in the terminal:
./build/bin/llama-cli -hf steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF:Q6_K_H

Use Docker

docker model run hf.co/steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF:Q6_K_H

LM Studio
Jan
Ollama
How to use steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF with Ollama:
```
ollama run hf.co/steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF:Q6_K_H
```

Unsloth Studio new

How to use steampunque/Qwen2.5-Coder-7B-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-7B-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-7B-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-7B-Instruct-MP-GGUF to start chatting

Pi new

How to use steampunque/Qwen2.5-Coder-7B-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-7B-Instruct-MP-GGUF:Q6_K_H

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-7B-Instruct-MP-GGUF:Q6_K_H"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use steampunque/Qwen2.5-Coder-7B-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-7B-Instruct-MP-GGUF:Q6_K_H

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-7B-Instruct-MP-GGUF:Q6_K_H

Run Hermes

hermes

Docker Model Runner
How to use steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF with Docker Model Runner:
```
docker model run hf.co/steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF:Q6_K_H
```

Lemonade

How to use steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF:Q6_K_H

Run and chat with the model

lemonade run user.Qwen2.5-Coder-7B-Instruct-MP-GGUF-Q6_K_H

List all available models

lemonade list

Mixed Precision GGUF layer quantization of Qwen2.5-Coder-7B-Instruct by Qwen

Original model: https://huggingface.co/Qwen/Qwen2.5-Coder-7B-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.

Q6_K_H layer quants are as follows:

Q5_K_L : attn_v = q8_0 attn_o = q6_k ffn_d = q6_k
Q6_K_S : Q6_K
Q6_K_M : attn_v = q8_0 ffn_d = q8_0
Q6_K_L : attn_v = q8_0 attn_o = q8_0 ffn_d = q8_0

LAYER_TYPES='[
   [0 ,"Q6_K_M"],[1 ,"Q5_K_L"],[2 ,"Q5_K_M"],[3 ,"Q5_K_M"],[4 ,"Q5_K_M"],[5 ,"Q5_K_M"],[6 ,"Q5_K_M"],
   [7 ,"Q5_K_L"],[8 ,"Q5_K_M"],[9 ,"Q5_K_L"],[10,"Q5_K_M"],[11,"Q5_K_L"],[12,"Q5_K_M"],[13,"Q5_K_L"],
   [14,"Q6_K_S"],[15,"Q5_K_L"],[16,"Q6_K_S"],[17,"Q5_K_L"],[18,"Q6_K_S"],[19,"Q6_K_M"],[20,"Q6_K_S"],
   [21,"Q6_K_M"],[22,"Q6_K_L"],[23,"Q6_K_L"],[24,"Q6_K_L"],[25,"Q6_K_L"],[26,"Q6_K_L"],[27,"Q8_0"]
   ]'
   FLAGS="--token-embedding-type Q6_K --output-tensor-type Q6_K --layer-types-high"

A second smaller Q4_K_H quant is also available:

Q4_K_L : Q4_K_M + attn_o = q6_k

LAYER_TYPES='[
   [0 ,"Q4_K_L"],[1 ,"Q4_K_M"],[2 ,"Q4_K_S"],[3 ,"Q4_K_M"],[4 ,"Q4_K_S"],[5 ,"Q4_K_M"],[6 ,"Q4_K_S"],
   [7 ,"Q4_K_S"],[8 ,"Q4_K_M"],[9 ,"Q4_K_S"],[10,"Q4_K_M"],[11,"Q4_K_S"],[12,"Q4_K_M"],[13,"Q4_K_S"],
   [14,"Q4_K_M"],[15,"Q4_K_S"],[16,"Q4_K_M"],[17,"Q4_K_S"],[18,"Q4_K_M"],[19,"Q4_K_M"],[20,"Q4_K_M"],
   [21,"Q4_K_L"],[22,"Q4_K_M"],[23,"Q4_K_L"],[24,"Q4_K_M"],[25,"Q4_K_L"],[26,"Q4_K_L"],[27,"Q5_K_M"]
   ]'
   FLAGS="--token-embedding-type Q4_K --output-tensor-type Q6_K --layer-types-high"

These quants were 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	4.25e9	9.4	-
Q4_K_H	4.8e9	9.4	Hybrid quant with Q4_K embedding Q6_K output
Q6_K	6.3e9	9.3	-
Q6_K_H	6.2e9	9.3	Hybrid quant with Q6_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 12G VRAM 4070 with weigths and context in VRAM:

Q	QKV	NKV	gen tps	spec gen tps	Comment
Q4_K_H	F16	32k	90	175	VRAM left over
Q4_K_H	F16	83k	90	134	VRAM full
Q4_K_H	Q8_0	32k	90	138	-
Q4_K_H	Q8_0	128k	90	176	VRAM full
Q6_K_H	F16	32k	75	130	-
Q6_K_H	F16	66k	75	124	-
Q6_K_H	Q8_0	32k	75	158	-
Q6_K_H	Q8_0	102k	75	124	-

for speculation a fixed length 10 token draft was used with a custom downstream speculator.

Benchmarks:

A full set of code benchmarks for the two quants are given here: https://huggingface.co/spaces/steampunque/benchlm

Download the file from below:

Link	Type	Size/e9 B	Notes
Qwen2.5-Coder-7B-Instruct.Q4_K_H.gguf	Q4_K_H	4.8e9 B	1.4B smaller than Q6_K_H
Qwen2.5-Coder-7B-Instruct.Q6_K_H.gguf	Q6_K_H	6.2e9 B	~Q6_K size

A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository:

https://github.com/ggml-org/llama.cpp/discussions/13040

Downloads last month: 72

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

6-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for steampunque/Qwen2.5-Coder-7B-Instruct-MP-GGUF

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Quantized

(191)

this model