Instructions to use noctrex/Qwopus3.5-9B-Coder-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use noctrex/Qwopus3.5-9B-Coder-MTP with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="noctrex/Qwopus3.5-9B-Coder-MTP",
	filename="Qwopus3.5-9B-Coder-MTP-IQ3_M.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use noctrex/Qwopus3.5-9B-Coder-MTP with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

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 noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

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 noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

Use Docker

docker model run hf.co/noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

LM Studio
Jan

vLLM

How to use noctrex/Qwopus3.5-9B-Coder-MTP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "noctrex/Qwopus3.5-9B-Coder-MTP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "noctrex/Qwopus3.5-9B-Coder-MTP",
		"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/noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

Ollama
How to use noctrex/Qwopus3.5-9B-Coder-MTP with Ollama:
```
ollama run hf.co/noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL
```

Unsloth Studio new

How to use noctrex/Qwopus3.5-9B-Coder-MTP 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 noctrex/Qwopus3.5-9B-Coder-MTP 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 noctrex/Qwopus3.5-9B-Coder-MTP to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for noctrex/Qwopus3.5-9B-Coder-MTP to start chatting

Pi new

How to use noctrex/Qwopus3.5-9B-Coder-MTP with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

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": "noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use noctrex/Qwopus3.5-9B-Coder-MTP with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

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 noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use noctrex/Qwopus3.5-9B-Coder-MTP with Docker Model Runner:
```
docker model run hf.co/noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL
```

Lemonade

How to use noctrex/Qwopus3.5-9B-Coder-MTP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull noctrex/Qwopus3.5-9B-Coder-MTP:Q4_K_XL

Run and chat with the model

lemonade run user.Qwopus3.5-9B-Coder-MTP-Q4_K_XL

List all available models

lemonade list

noctrex commited on 7 days ago

Commit

941f561

verified ·

1 Parent(s): 3cfdbc6

Add files using upload-large-folder tool

Browse files

Files changed (7) hide show

.gitattributes +5 -0
Qwopus3.5-9B-Coder-MTP-IQ4_XS.gguf +3 -0
Qwopus3.5-9B-Coder-MTP-Q4_K_XL.gguf +3 -0
Qwopus3.5-9B-Coder-MTP-Q6_K.gguf +3 -0
Qwopus3.5-9B-Coder-MTP-Q8_0.gguf +3 -0
README.md +17 -0
imatrix-code_micro.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+imatrix-code_micro.gguf filter=lfs diff=lfs merge=lfs -text
+Qwopus3.5-9B-Coder-MTP-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwopus3.5-9B-Coder-MTP-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwopus3.5-9B-Coder-MTP-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwopus3.5-9B-Coder-MTP-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text

Qwopus3.5-9B-Coder-MTP-IQ4_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a9ea62d65af07dda0a873f1940b0f3cf1142f19f20927a05d45b11a124486f
+size 6026814016

Qwopus3.5-9B-Coder-MTP-Q4_K_XL.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:92859bc5b0f10f5f819c7983155207700ba39613c0b85d5cbf7a7a630e50474a
+size 6238806592

Qwopus3.5-9B-Coder-MTP-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8a855aa24c5882ae918f328e4fe9a2cc0543e6f071cdfbc0e6fc01738107b3e5
+size 7617815104

Qwopus3.5-9B-Coder-MTP-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e639ca81579757e4f929da62fb0b4817d6b686600083537746417fefffbb65a5
+size 9786057312

README.md ADDED Viewed

	@@ -0,0 +1,17 @@

+---
+pipeline_tag: image-text-to-text
+base_model:
+- Jackrong/Qwopus3.5-9B-Coder
+tags:
+  - qwen
+  - qwen3_5_moe
+  - MTP
+---
+These are quantizations of the model [Jackrong / Qwopus3.5-9B-Coder](https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder)
+I've added the MTP layer on it.
+My personal speed improvement on my 7900XTX with the vulkan backend has been from ~80 tps to around ~120 tps.
+An imatrix has been calulated for coding tasks, as such it is specialized for coding.
+## Quick Start
+1. Download the latest release of **llama.cpp**.
+2. Download your preferred model variant from below.

imatrix-code_micro.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4076274f6bee37af8437f8fc9539d34a6206e2dec622ffcf16787f40f0fb2304
+size 5150176