Instructions to use mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("feature-extraction", model="mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless")
model = AutoModel.from_pretrained("mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless 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 mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0
# Run inference directly in the terminal:
llama cli -hf mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0
# Run inference directly in the terminal:
llama cli -hf mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

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 mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

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 mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

Use Docker

docker model run hf.co/mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

LM Studio
Jan
Ollama
How to use mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless with Ollama:
```
ollama run hf.co/mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0
```
Unsloth Desktop

How to use mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless with Docker Model Runner:
```
docker model run hf.co/mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0
```

Lemonade

How to use mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

Run and chat with the model

lemonade run user.qwen3.5-4l-vocab40k-en-ko-headless-Q8_0

List all available models

lemonade list

Hermes Agent

How to use mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

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 mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0

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 "mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless:Q8_0" \
  --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"

qwen3.5-4l-vocab40k-en-ko-headless / runtime /README.md

mp-juuuns

Replace the root with the task-blind 32k backbone; add figures, the full benchmark record and the ported runtime

c99961f verified 4 days ago

preview code

Raw

History Blame Contribute Delete

2.37 kB

Dedicated Q8 runtime, ported to accept a cut vocabulary

The shipped dedicated runtime (deployment/qwen35-specialized-v3 in the research repository) is a patched llama.cpp that fuses this architecture's recurrent path and runs the 14-label head natively. It refused any vocabulary other than 128,000 at two points:

where	check
`qwen35-classifier.cpp`	`llama_vocab_n_tokens(...) != 128000` -> throw
`src/models/qwen35.cpp`	`GGML_ASSERT(n_layer == 4 && n_embd == 1024 && tok_embd->ne[1] == 128000)`

Both are model-identity guards, not computational dependencies: the specialised tail keeps the last four token rows and skips inp_out_ids, and reads n_embd, n_cls_out, n_seqs and n_tokens only. The hand-written Q8 kernels operate on hidden 1024. The two files here are those sources with the vocabulary equality relaxed; architecture, depth and width are still enforced.

What was measured after the port

Three vocabulary cuts load and run at full specialisation level, with output bit-identical to the generic path, and lower native compute:

cut	tokens in probe	level 0	level 12	change
v16k	33	14.94 ms	10.68 ms	-28.5%
v32k	25	11.47 ms	7.36 ms	-35.8%
v64k	23	10.32 ms	7.26 ms	-29.7%

Token counts differ per cut for the same sentence, so compare within a row, not across rows.

Boundaries

This is a development port. It has not been through the v3 validation scripts (validate_runtime.py, validate_reload.py, validate_threads_service.py).
The timings above are single-sentence native compute medians on a host with a desktop session running, not the benchmark's isolated document-level protocol. No number in the model card came from this runtime; those came from the benchmark's own profile_inference.py.
The runtime needs a GGUF with a classification head. The repository root is headless, so train a head first and convert that checkpoint.
aarch64 / A53 NEON variants were not built or tested.
The five binaries of the frozen v3 build are unchanged; every sha256 still matches.

Files

file	sha256
`qwen35-classifier.cpp`	`76ede06e20b4f23fb57799e93ac4cafd0d02f068c1215bb30f7ce53c7ae76eba`
`qwen35.cpp`	`10453eaae33efaa53790d6e28ed72459342927b86e9ff888db11527b36d74225`