Instructions to use unsloth/Qwen3-Coder-Next-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Qwen3-Coder-Next-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Qwen3-Coder-Next-GGUF",
	filename="BF16/Qwen3-Coder-Next-BF16-00001-of-00004.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 unsloth/Qwen3-Coder-Next-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 unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3-Coder-Next-GGUF:UD-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 unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3-Coder-Next-GGUF:UD-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 unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M

Use Docker

docker model run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M

LM Studio
Jan

vLLM

How to use unsloth/Qwen3-Coder-Next-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3-Coder-Next-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": "unsloth/Qwen3-Coder-Next-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M

Ollama
How to use unsloth/Qwen3-Coder-Next-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M
```

Unsloth Studio

How to use unsloth/Qwen3-Coder-Next-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 unsloth/Qwen3-Coder-Next-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 unsloth/Qwen3-Coder-Next-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/Qwen3-Coder-Next-GGUF to start chatting

How to use unsloth/Qwen3-Coder-Next-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M

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": "unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Qwen3-Coder-Next-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 unsloth/Qwen3-Coder-Next-GGUF:UD-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 unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use unsloth/Qwen3-Coder-Next-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3-Coder-Next-GGUF:UD-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 "unsloth/Qwen3-Coder-Next-GGUF:UD-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"

Docker Model Runner
How to use unsloth/Qwen3-Coder-Next-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M
```

Lemonade

How to use unsloth/Qwen3-Coder-Next-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-Coder-Next-GGUF-UD-Q4_K_M

List all available models

lemonade list

does not work with ollama 0.15.5 - 0.15.6

by asg345asdf - opened Feb 8

Discussion

asg345asdf

Feb 8

(base) ➜  ~ ollama --version                             
ollama version is 0.15.6
(base) ➜  ~ ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:Q4_K_M
Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.ssm_in.weight'
llama_model_load_from_file_impl: failed to load model

asg345asdf changed discussion title from does not work with 0.15.5 - 0.15.6 to does not work with ollama 0.15.5 - 0.15.6 Feb 8

threadj

Feb 8

•

edited Feb 8

Same here. I'm trying to run this on a RTX Pro 6000 96G:

$ docker exec -it ollama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:latest
Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.ssm_in.weight'

$ docker exec -it ollama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:Q4_K_M
Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.ssm_in.weight'

$ docker exec -it ollama ollama --version
ollama version is 0.15.6

asg345asdf

Feb 8

llama_model_load: error loading model: missing tensor 'blk.0.ssm_in.weight'
llama_model_load_from_file_impl: failed to load model
panic: unable to load model: /ollama_models/blobs/sha256-eab53ec181795fd2b35cf875ccaa76cb19bab27f7b3d47ffc0cafbc5e196ecb2

and strings /ollama_models/blobs/sha256-eab53ec181795fd2b35cf875ccaa76cb19bab27f7b3d47ffc0cafbc5e196ecb2 | grep "blk.0.ssm_in.weight" doesnt return anything, maybe its actually missing?

asg345asdf

Feb 8

•

edited Feb 8

INFO:gguf-dump:* Loading: /ollama_models/blobs/sha256-eab53ec181795fd2b35cf875ccaa76cb19bab27f7b3d47ffc0cafbc5e196ecb2
      4:    8388608 |  2048,  4096,     1,     1 | Q4_K    | blk.0.attn_gate.weight
      5:       2048 |  2048,     1,     1,     1 | F32     | blk.0.attn_norm.weight
      6:   16777216 |  2048,  8192,     1,     1 | Q5_K    | blk.0.attn_qkv.weight
      7:  536870912 |   512,  2048,   512,     1 | Q6_K    | blk.0.ffn_down_exps.weight
      8:    1048576 |   512,  2048,     1,     1 | Q6_K    | blk.0.ffn_down_shexp.weight
      9:  536870912 |  2048,   512,   512,     1 | Q4_K    | blk.0.ffn_gate_exps.weight
     10:    1048576 |  2048,   512,     1,     1 | F32     | blk.0.ffn_gate_inp.weight
     11:       2048 |  2048,     1,     1,     1 | BF16    | blk.0.ffn_gate_inp_shexp.weight
     12:    1048576 |  2048,   512,     1,     1 | Q5_K    | blk.0.ffn_gate_shexp.weight
     13:  536870912 |  2048,   512,   512,     1 | Q4_K    | blk.0.ffn_up_exps.weight
     14:    1048576 |  2048,   512,     1,     1 | Q5_K    | blk.0.ffn_up_shexp.weight
     15:       2048 |  2048,     1,     1,     1 | F32     | blk.0.post_attention_norm.weight
     16:         32 |    32,     1,     1,     1 | F32     | blk.0.ssm_a
     17:     131072 |  2048,    64,     1,     1 | Q4_K    | blk.0.ssm_ba.weight
     18:      32768 |     4,  8192,     1,     1 | F32     | blk.0.ssm_conv1d.weight
     19:         32 |    32,     1,     1,     1 | F32     | blk.0.ssm_dt.bias
     20:        128 |   128,     1,     1,     1 | F32     | blk.0.ssm_norm.weight
     21:    8388608 |  4096,  2048,     1,     1 | Q4_K    | blk.0.ssm_out.weight

no blk.0.ssm_in.weight

reswewr

Feb 8

same problem here with ollama v0.15.6

shimmyshimmer

Unsloth AI org Feb 9

•

edited Feb 9

Starting from late last year, GGUFs don't work out of the gate with Ollama anymore, so, at the moment we only recommend using GGUFs with llama.cpp compatible backends

Arbiger

Feb 15

Starting from late last year, GGUFs don't work out of the gate with Ollama anymore, so, at the moment we only recommend using GGUFs with llama.cpp compatible backends

Thanks, any clue if they will update it?

deiangi

Feb 18

ollama --version
ollama version is 0.16.2

ollama run hf.co/lovedheart/Qwen3-Coder-Next-REAP-60B-A3B-GGUF:Q3_K_XL
Error: 500 Internal Server Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.ssm_in.weight'

DannyEli

Feb 23

The same issue is still present for Ollama version 0.17.0

AlexPpop

Feb 27

Same here - Ollama latest version

Arbiger

Feb 27

I remembered it because ollama do not support the latest qunatize format, I use LM Studio instead.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment