Instructions to use Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT", filename="mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00001-of-00024.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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT # Run inference directly in the terminal: llama-cli -hf Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT # Run inference directly in the terminal: llama-cli -hf Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT # Run inference directly in the terminal: ./llama-cli -hf Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT # Run inference directly in the terminal: ./build/bin/llama-cli -hf Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
Use Docker
docker model run hf.co/Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
- LM Studio
- Jan
- Ollama
How to use Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT with Ollama:
ollama run hf.co/Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
- Unsloth Studio
How to use Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT to start chatting
- Pi
How to use Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
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-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT with Docker Model Runner:
docker model run hf.co/Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
- Lemonade
How to use Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Thireus/mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT
Run and chat with the model
lemonade run user.mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_SPLIT-{{QUANT_TAG}}List all available models
lemonade list
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00002-of-00024.gguf:d76dee061910b49588b5d336ace7df3b631a10f8f782c0ec6eae963b915f1dae:output.weight:shape=(2048, 248320):dtype=iq5_k_r4:elements=508559360:bytes=349634560 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00003-of-00024.gguf:c690e499053346d43a736745ca9e8e97570989d61422b6e94c2e1da71c4e21c5:token_embd.weight:shape=(2048, 248320):dtype=iq5_k:elements=508559360:bytes=349634560 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00004-of-00024.gguf:fdfcc9b9b4fa1c309cd1878499e466c039ffa69cc190f4220ddb71eb39675923:blk.40.nextn.eh_proj.weight:shape=(4096, 2048):dtype=iq5_k_r4:elements=8388608:bytes=5767168 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00005-of-00024.gguf:badbd67d959d5168b2e4320c2fb5fee2c21a0a15355a4bbaba06d9085a69ff9b:blk.40.attn_output.weight:shape=(4096, 2048):dtype=iq5_k_r4:elements=8388608:bytes=5767168 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00006-of-00024.gguf:8b4f71a6434768d27bca8213edec6004ce122cfd8bcfedfb75b668102945ea52:blk.40.attn_q.weight:shape=(2048, 8192):dtype=iq5_k_r4:elements=16777216:bytes=11534336 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00007-of-00024.gguf:c5be725838e806331bae127a6bcc3ac3f2f680b3df82e515048fdd0a419d59ea:output_norm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00008-of-00024.gguf:08beb9c6e7cd3a1acff6b4090ea320030bcdf4c0dec9be598fca725fe20fe407:blk.40.attn_norm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00009-of-00024.gguf:4ad1e82966a9a49243447603624ef4fee13def5389afcafea4dd314f7421abbb:blk.40.ffn_down_exps.weight:shape=(512, 2048, 256):dtype=iq5_k_r4:elements=268435456:bytes=184549376 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00010-of-00024.gguf:1da34bd2b0cd681760e343b6ba6a1cd8a3f539bdbaef929888dcbc46fcb626e8:blk.40.ffn_gate_exps.weight:shape=(2048, 512, 256):dtype=iq5_k_r4:elements=268435456:bytes=184549376 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00011-of-00024.gguf:3434f4c4efdd33d8da58e1a0d3ec4e0da7546471e627248a7759395885c06d00:blk.40.ffn_up_exps.weight:shape=(2048, 512, 256):dtype=iq5_k_r4:elements=268435456:bytes=184549376 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00012-of-00024.gguf:b0df2b2fac171285aa30dfab04178fa7364559ea78e460291e7c3cb1236ebc58:blk.40.ffn_gate_inp.weight:shape=(2048, 256):dtype=bf16:elements=524288:bytes=1048576 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00013-of-00024.gguf:199e7cd3464994379d427cd1ac7d95d7779105759a03660251eba952a3ff89fe:blk.40.ffn_down_shexp.weight:shape=(512, 2048):dtype=iq5_k_r4:elements=1048576:bytes=720896 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00014-of-00024.gguf:7ee114eb8caa46f0fefa183c526376e627ad70bb768f8e552a2500ce8991c95b:blk.40.ffn_gate_shexp.weight:shape=(2048, 512):dtype=iq5_k_r4:elements=1048576:bytes=720896 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00015-of-00024.gguf:6b7dc6a8507e0447aac97f5ded7aa85ea32d3f190bf7434a0207abef572d7f6e:blk.40.ffn_up_shexp.weight:shape=(2048, 512):dtype=iq5_k_r4:elements=1048576:bytes=720896 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00016-of-00024.gguf:3fc254211402f7e451d19990392d7a912ddaaed128aff56a44fd47094d73e450:blk.40.ffn_gate_inp_shexp.weight:shape=(2048,):dtype=bf16:elements=2048:bytes=4096 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00017-of-00024.gguf:05f1430d54301a4f21f6fb4221e7fd7276284136886549c172a66cee3310d770:blk.40.post_attention_norm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00018-of-00024.gguf:ab43e7c05f7055fcf1afbaf9bb7ccdeac21d22cd706460bb7ec157e7a696158b:blk.40.attn_k_norm.weight:shape=(256,):dtype=f32:elements=256:bytes=1024 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00019-of-00024.gguf:a2710424d996d2fb66e8e815f4fd9cdacc4be83b69c71048ec9570594fe26f64:blk.40.attn_k.weight:shape=(2048, 512):dtype=iq5_k_r4:elements=1048576:bytes=720896 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00020-of-00024.gguf:125d7b98d544e743112c447d6c1fbb29192a3fb42dfaff04b6deaff4d2148aca:blk.40.attn_q_norm.weight:shape=(256,):dtype=f32:elements=256:bytes=1024 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00021-of-00024.gguf:2da524497a2052387fa23d9cd07da7625806b41d582f5678dcdb45a1fad7c6a6:blk.40.attn_v.weight:shape=(2048, 512):dtype=iq5_k_r4:elements=1048576:bytes=720896 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00022-of-00024.gguf:1e5489650f37c6b333039b1511170a6b339f52418c2c78b0b93b015e8046d53a:blk.40.nextn.shared_head_norm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00023-of-00024.gguf:c1e6023e08d7b91a3c4daeda24497868e1c98db437b4868b5246bc6e00a6f23b:blk.40.nextn.enorm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192 | |
| mtp-Qwen3.5-35B-A3B-THIREUS-IQ5_K_R4-SPECIAL_TENSOR-00024-of-00024.gguf:017b7d8a8774eeeb7458061453f3a2d39d56c1b30fc9ecba739ed65741be03cc:blk.40.nextn.hnorm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192 | |