Skip to content
ModelVerifiedExternal
Download

Mtp Qwen3.5 397B A17B THIREUS IQ2 S SPECIAL SPLIT

This repository provides GGUF-quantized tensors for the mtp layer(s) of the Qwen3.5-397B-A17B model (official repo: These GGUF shards are designed to be used with Thireus’ GGUF Tool Suite ( a collection of tools that...

Sourcehuggingface.co/Thireus/mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_SPLIT/tree/d90b7d9baf4c29c03ec42ea7692e2c845ad11997
KindOtherVersionRevision d90b7d9Publisher@ThireusCgrade

Model source

Kind
Other
File size
1.19 KB–592 MB
Version
vRevision d90b7d9
Updated
Sep 17, 2026
Publisher
@Thireus
Downloads
2
Parameters
397B
Source
Hugging Face

Source excerpt

This repository provides GGUF-quantized tensors for the mtp layer(s) of the Qwen3.5-397B-A17B model (official repo: These GGUF shards are designed to be used with Thireus’ GGUF Tool Suite ( a collection of tools that...

Sources

1 source
Hugging FacePrimaryVersion d90b7d9baf4c29c03ec42ea7692e2c845ad11997
huggingface.co/Thireus/mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_SPLIT/tree/d90b7d9baf4c29c03ec42ea7692e2c845ad11997

Verified Sep 1

Model artifacts

24 artifacts

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00001-of-00024.gguf

gguf · 10.4 MB · SHA-256 652c8f1642d2…8582 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00002-of-00024.gguf

gguf · 280 MB · SHA-256 6c11f3c48a45…46d1 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00003-of-00024.gguf

gguf · 280 MB · SHA-256 26b7e562d728…1bbe · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00004-of-00024.gguf

gguf · 18.5 MB · SHA-256 b84a39df945d…a9f3 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00005-of-00024.gguf

gguf · 9.25 MB · SHA-256 fd255a11fa68…4a81 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00006-of-00024.gguf

gguf · 9.25 MB · SHA-256 08ba6d099102…749c · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00007-of-00024.gguf

gguf · 16.2 KB · SHA-256 2439e05c75a1…1df0 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00008-of-00024.gguf

gguf · 16.2 KB · SHA-256 1a383841b9c1…c9eb · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00009-of-00024.gguf

gguf · 592 MB · SHA-256 15f8419db902…8c76 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00010-of-00024.gguf

gguf · 592 MB · SHA-256 35ab83bbd4bf…d040 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00011-of-00024.gguf

gguf · 592 MB · SHA-256 7ea54066a123…770b · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00012-of-00024.gguf

gguf · 4.00 MB · SHA-256 5700fd87103c…4a37 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00013-of-00024.gguf

gguf · 1.16 MB · SHA-256 716967ff450d…8651 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00014-of-00024.gguf

gguf · 1.16 MB · SHA-256 8062d986ec15…2c72 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00015-of-00024.gguf

gguf · 1.16 MB · SHA-256 bd51870c459e…135b · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00016-of-00024.gguf

gguf · 8.19 KB · SHA-256 da01c2854a2b…117b · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00017-of-00024.gguf

gguf · 16.2 KB · SHA-256 31c12485ad73…ab28 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00018-of-00024.gguf

gguf · 1.19 KB · SHA-256 b1dd08c4fa66…ed30 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00019-of-00024.gguf

gguf · 592 KB · SHA-256 5f2b0974b6e6…dd54 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00020-of-00024.gguf

gguf · 1.19 KB · SHA-256 13d11323507a…3419 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00021-of-00024.gguf

gguf · 592 KB · SHA-256 576b5de63223…3f52 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00022-of-00024.gguf

gguf · 16.2 KB · SHA-256 5f9192fcd24a…ed08 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00023-of-00024.gguf

gguf · 16.2 KB · SHA-256 64ef3cc4d66a…ba13 · Hugging Face

Download

mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_TENSOR-00024-of-00024.gguf

gguf · 16.2 KB · SHA-256 3770f6f1db4c…5da7 · Hugging Face

Download

Source excerpts

3 excerpts
ReadmeJul 11huggingface.co/Thireus/mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_SPLIT

--- license: mit --- # mtp-Qwen3.5-397B-A17B ## 🤔 What is this [HuggingFace repository](https://huggingface.co/Thireus/mtp-Qwen3.5-397B-A17B-THIREUS-BF16-SPECIAL_SPLIT/) about? This repository provides **GGUF-quantized tensors** for the [mtp](https://github.com/ggml-org/llama.cpp/blob/master/docs/speculative.md) layer(s) of the Qwen3.5-397B-A17B model (official repo: https://huggingface.co/Qwen/Qwen3.5-397B-A17B). These GGUF shards are designed to be used with **Thireus’ GGUF Tool Suite** (https://github.com/Thireus/GGUF-Tool-Suite), a collection of tools that automatically finds the perplexity-optimal mix of quantizations for any given a model size target. With this GGUF Tool Suite, you can produce your own Dynamic 3.0 Quants recipes and achieve optimum accuracy & SOTA quantization performance. Give it a try here: https://gguf.thireus.com/quant_assign.html - 📖 Documentation: https://github.com/Thireus/GGUF-Tool-Suite/tree/main/docs - 🔍 Example of GGUF recipes: https://github.com/Thireus/GGUF-Tool-Suite/tree/main/recipe_examples - 🍳 Cook your own recipe files: https://gguf.thireus.com/quant_assign.html - ☁️ Download GGUF models from recipe files: https://gguf.thireus.com/quant_downloader.html - 📂 Browse available models: https://huggingface.co/Thireus/collections and https://gguf.thireus.com *tl;dr: Expand the details section below* <details> ``` cd ~ # Make sure to install all ik_llama.cpp compilation dependencies... apt install python3-dev python3-pip python3-venv python3-wheel python3-setuptools git acl netcat-openbsd cmake # pipx # Obtain ik_llama's Thireus version - Windows/macOS/Linux builds available at https://github.com/Thireus/ik_llama.cpp/releases git clone https://github.com/Thireus/ik_llama.cpp cd ik_llama.cpp git pull # Build ik_llama.cpp cmake -B build -DGGML_AVX=ON -DGGML_AVX2=ON -DLLAMA_CURL=OFF -DGGML_MAX_CONTEXTS=2048 cmake --build build --config Release -j16 cd .. # Obtain Thireus' GGUF-Tool-Suite GIT_LFS_SKIP_SMUDGE=1 git clone https://github.com/Thireus/GGUF-Tool-Suite # Download model quant mix from recipe file - you can also try the web version: https://gguf.thireus.com/quant_downloader.html cd GGUF-Tool-Suite rm -f download.conf # Make sure to copy the relevant download.conf for the model before running quant_assign.py cp -f models/Qwen3.5-397B-A17B/download.conf . # Use the download.conf of the chosen model mkdir -p...

NoteSep 1huggingface.co/Thireus/mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_SPLIT

Source context: 2 downloads · 0 likes · Repo Thireus/mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_SPLIT

NoteJul 17huggingface.co/Thireus/mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_SPLIT

Source context: 4 downloads · 0 likes · Repo Thireus/mtp-Qwen3.5-397B-A17B-THIREUS-IQ2_S-SPECIAL_SPLIT