Instructions to use Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT",
	filename="mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00001-of-00018.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R
# Run inference directly in the terminal:
llama-cli -hf Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R
# Run inference directly in the terminal:
llama-cli -hf Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R

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 Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R
# Run inference directly in the terminal:
./llama-cli -hf Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R

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 Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R

Use Docker

docker model run hf.co/Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R

LM Studio
Jan
Ollama
How to use Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT with Ollama:
```
ollama run hf.co/Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R
```

Unsloth Studio

How to use Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT 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 Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT 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 Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT to start chatting

How to use Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R

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": "Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R

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 Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT with Docker Model Runner:
```
docker model run hf.co/Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R
```

Lemonade

How to use Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Thireus/mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT:IQ1_S_R

Run and chat with the model

lemonade run user.mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT-IQ1_S_R

List all available models

lemonade list

mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT / tensors.map

Thireus

mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_SPLIT

70ea3a0 28 days ago

Raw

History Blame Contribute Delete

3.66 kB

	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00002-of-00018.gguf:5effdddc404bd3909cd20af7d0a8041214189c1904952beb3b48a418033fc493:token_embd.weight:shape=(1024, 248320):dtype=iq1_m:elements=254279680:bytes=55623680
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00003-of-00018.gguf:9b64e634634350dfd25134a38369befc9bfc471299f808215898802db2c8fce7:output_norm.weight:shape=(1024,):dtype=f32:elements=1024:bytes=4096
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00004-of-00018.gguf:58f6fca4fd2e9ce5ae826a4784496601b9d8a0b6febdf0f2988047ab308d8d97:blk.24.nextn.eh_proj.weight:shape=(2048, 1024):dtype=iq1_s_r4:elements=2097152:bytes=395264
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00005-of-00018.gguf:4950b226e820ceb63826b4690cfe3016c5b3795a0e0bbffbededb4a95a6458a8:blk.24.attn_norm.weight:shape=(1024,):dtype=f32:elements=1024:bytes=4096
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00006-of-00018.gguf:dea3f0e8739899998379c23c044b76932d24b771be1523296d6e19a2fe8d9626:blk.24.ffn_down.weight:shape=(3584, 1024):dtype=iq1_s_r4:elements=3670016:bytes=690176
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00007-of-00018.gguf:8521754483a5e216891e8369ec7452ea4d5a41a3358c9964dd501ff699966b2c:blk.24.ffn_gate.weight:shape=(1024, 3584):dtype=iq1_s_r4:elements=3670016:bytes=695296
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00008-of-00018.gguf:0089f992970d79d1b77c68cc6c55b5d262311eec80d903920332e8f2cfa967d2:blk.24.ffn_up.weight:shape=(1024, 3584):dtype=iq1_s_r4:elements=3670016:bytes=695296
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00009-of-00018.gguf:eefa795fe164cb7d5968fc5c7f2df508c65a316085b55c3ecabdcac1870eff64:blk.24.post_attention_norm.weight:shape=(1024,):dtype=f32:elements=1024:bytes=4096
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00010-of-00018.gguf:5ac5a69e5a84a8988842c1e41af923364dfcc2f68ff3750b8480f9de48290633:blk.24.attn_k_norm.weight:shape=(256,):dtype=f32:elements=256:bytes=1024
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00011-of-00018.gguf:731204a1782ef192fa11601bcb98cd5e1b8900dc2e28cd2d6af5a8d1a14a6590:blk.24.attn_k.weight:shape=(1024, 512):dtype=iq1_s_r4:elements=524288:bytes=99328
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00012-of-00018.gguf:272663f205760094314cbbf029f7d19266beb7a9fe4991da349c70de0438d39a:blk.24.attn_output.weight:shape=(2048, 1024):dtype=iq1_s_r4:elements=2097152:bytes=395264
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00013-of-00018.gguf:515f032bd4b22c2b1dd6f11b5b11595b4e1b18513dbcd73e288c799bce54a3bf:blk.24.attn_q_norm.weight:shape=(256,):dtype=f32:elements=256:bytes=1024
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00014-of-00018.gguf:dd75b251ac5c6d8f9cdccd4bf8d1ad6c9036393ee9be112c123bb9b3e0dc6789:blk.24.attn_q.weight:shape=(1024, 4096):dtype=iq1_s_r4:elements=4194304:bytes=794624
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00015-of-00018.gguf:23ca9f355f96360de7febe86a5fd990c59887822b9d7e3fb20e4b2cb24894f67:blk.24.attn_v.weight:shape=(1024, 512):dtype=iq1_s_r4:elements=524288:bytes=99328
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00016-of-00018.gguf:aa9d706f3a2c6bac1919836e3984b86e3a891558ba14fcbaae0db105d82048a7:blk.24.nextn.shared_head_norm.weight:shape=(1024,):dtype=f32:elements=1024:bytes=4096
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00017-of-00018.gguf:242ddc673551d365aa87d658eab3a00edd87b4625f9dd05dd57dcb6275491d60:blk.24.nextn.enorm.weight:shape=(1024,):dtype=f32:elements=1024:bytes=4096
	mtp-Qwen3.5-0.8B-THIREUS-IQ1_S_R4-SPECIAL_TENSOR-00018-of-00018.gguf:4be36458c8730327b177e3448c8f38ab96e8c5e87c8db619ea63aeff62834049:blk.24.nextn.hnorm.weight:shape=(1024,):dtype=f32:elements=1024:bytes=4096