mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_SPLIT

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
+*.gguf.zbst filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,158 @@
 ---
 license: mit
 ---
+# mtp-Qwen3.6-35B-A3B
+
+## 🤔 What is this [HuggingFace repository](https://huggingface.co/Thireus/mtp-Qwen3.6-35B-A3B-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 Qwen3.6-35B-A3B model (official repo: https://huggingface.co/Qwen/Qwen3.6-35B-A3B). 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/Qwen3.6-35B-A3B/download.conf . # Use the download.conf of the chosen model
+mkdir -p kitchen && cd kitchen
+# Obtain a recipe example for the chosen model from ../recipe_examples/
+../quant_downloader.sh ../recipe_examples/ik_llama.cpp_recipes/Qwen3.6-35B-A3B.ROOT-3.5993bpw-11.3565ppl.1GB-GGUF_0GB-GPU_0GB-CPU.9888e4b_831ff04.recipe
+
+# Other recipe examples can be found at https://github.com/Thireus/GGUF-Tool-Suite/tree/main/recipe_examples
+
+# Launch ik_llama's llama-cli:
+ulimit -n 9999 # Lifts "too many open files" limitation on Linux
+~/ik_llama.cpp/build/bin/llama-server \
+  -m Qwen3.6-35B-A3B-THIREUS-BF16-SPECIAL_TENSOR-00001-of-*.gguf \
+  -md mtp-Qwen3.6-35B-A3B-THIREUS-BF16-SPECIAL_TENSOR-00001-of-*.gguf --spec-type draft-mtp \
+  -fa auto -amb 1024 -ctk q8_0 -c 32768 -ngl 99 \
+  -b 4096 -ub 4096 --warmup-batch --no-mmap --threads 1 \
+  --main-gpu 0
+```
+
+</details>
+
+---
+
+## ❓ Why does this Tool Suite exist?
+
+1. **Compatibility & Speed** – [unsloth](https://huggingface.co/unsloth)’s dynamic quants may not always work optimally with `ik_llama.cpp`.  
+2. **Custom Rig Fit** – No off-the-shelf GGUF model perfectly matched my VRAM/RAM setup, so I built a way to tailor models and leverage extra VRAM/RAM to reduce perplexity.  
+3. **Automated PPL-Optimal Quantization** – To my knowledge, there was no open source flexible, automated method to minimize perplexity for any bits-per-weight (bpw) target—so I created one with excellent results!  
+
+---
+
+## 📊 How does it compare to other GGUFs?
+
+Here’s how Qwen3.6-35B-A3B quantized with **Thireus’ GGUF Tool Suite** stacks up against other quantizers (lower perplexity = better at equal or lower bpw):
+
+![PPLs Compared With Others](https://github.com/Thireus/GGUF-Tool-Suite/raw/main/ppl_graphs/Qwen3.6-35B-A3B.svg)
+
+> _Note: The `recipe_examples` files illustrate good recipes. The Tool Suite computes the optimal ppl/bpw curve for you — just specify your target RAM, VRAM, and quant types, and `quant_assign.py` finds the best mix._  
+
+More perplexity/bpw graphs for other supported models: https://github.com/Thireus/GGUF-Tool-Suite/tree/main/ppl_graphs  
+
+*Qwen3.6 Thireus' PPL benchmarks are computed with the parameters `-ctk f16 -c 512 -b 512 -ub 512`. Changing any of these parameters will alter the PPL. In particular, reducing `-b 512 -ub 512` increases the PPL, while increasing them decreases the PPL.*
+
+---
+
+## 🚀 How do I get started?
+
+Check out the [GGUF Tool Suite README](https://github.com/Thireus/GGUF-Tool-Suite) — focus on these sections:
+
+1. ⚠️ **Requirements** – Which `ik_llama.cpp` (or `llama.cpp`) version to use and how to compile.  
+   - Windows binaries (no patching needed) at: https://github.com/Thireus/ik_llama.cpp/releases  
+2. 📥 **Download Model Shards** – Use `quant_downloader.sh` or [quant_downloader.html](https://gguf.thireus.com/quant_downloader.html) to fetch GGUF shards from any recipe.  
+   - Recipe examples: https://github.com/Thireus/GGUF-Tool-Suite/tree/main/recipe_examples  
+3. 🧠 **Run a Downloaded Model** – Sample usage with `llama-cli`.  
+4. 🛠️ **Generate a Custom Recipe** – Produce recipes tailored to your VRAM/RAM target usage for optimum perplexity.  
+
+---
+
+## ✅ Supported Models
+
+Supported models are listed under `models/` in the [Tool Suite Github repo](https://github.com/Thireus/GGUF-Tool-Suite/tree/main/models). Presence of `ppl_results.csv` indicates official support and compatibility with `quant_assign.py`.
+
+---
+
+## 🤷‍♂️ Will I release baked dynamic quant GGUFs?
+
+No, because I believe in **tailored quantization** for each user’s hardware. If you prefer ready-made shards, you are welcome to merge them via `llama-gguf-split --merge`, or request someone to publish them, or rely on generic GGUF dynamic quants such as [unsloth](https://huggingface.co/unsloth)'s.
+
+Instead, I prefer to share examples of recipes so users can see exactly how they were produced (command included inside these recipe files) and tweak them for their own rigs. The `quant_downloader.sh` script or [quant_downloader.html](https://gguf.thireus.com/quant_downloader.html) (web port of this script) handles automatic fetching and verification of each shard. Note that recipes provided by [Ubergarm](https://huggingface.co/ubergarm) on his model cards are also compatible with `quant_downloader.sh` and [quant_downloader.html](https://gguf.thireus.com/quant_downloader.html), providing a "SPECIAL_SPLIT" version of these models exists (see https://gguf.thireus.com/).
+
+Users who don’t trust the GGUF shards on HuggingFace can also quantize their own by passing recipe lines to `llama-quantize --custom-q` ([see example](https://github.com/Thireus/GGUF-Tool-Suite/blob/main/models/DeepSeek-R1-0528/DeepSeek-R1-0528-THIREUS-ANY-SPECIAL.sh#L482-L486)). Run `llama-quantize --help` to list compatible quants for `quant_assign.py`. This approach is especially useful if you prefer `llama.cpp` over `ik_llama.cpp`.  
+
+---
+
+## 📦 What’s in this repository?
+
+- **00001 GGUF header shard** – Contains metadata (tokens, chat template, tensor count, etc.). This metadata can be explored directly from the HuggingFace web interface after clicking on that shard.  
+- **Tensor shards** – Each shard holds one tensor; see `tensors.map` for names, quant types, sizes, SHA-256 hash, shard IDs, etc.  
+- **GPG-signed files** – `tensors.map` and header shard are signed with the key in [trusted-keys.asc](https://github.com/Thireus/GGUF-Tool-Suite/blob/main/trusted-keys.asc) for tamper detection.  
+- **Security note** – Some papers about various ways to attack GGUFs and LLMs are available online, such as https://arxiv.org/abs/2505.23786, and there are also more classic security exploits like CVE-2024-23496 and CVE-2024-25664 through CVE-2024-25668. Only use GGUFs from reputable, trusted authors—or alternatively self-quantize—to avoid potential exploits. 
+
+---
+
+## 💡 Pro Tips
+
+You can easily download the BF16 model version to quantize your own shards:
+
+```
+mkdir kitchen  
+echo '.*=bf16' > kitchen/bf16.recipe  
+cd kitchen
+../quant_downloader.sh bf16.recipe --qtype BF16 
+```
+
+You can also quantize individual BF16 tensors without the need to download every BF16 .gguf shard:
+
+BF16 model shards can also be individually quantized using a special version of ik_llama.cpp's `llama-quantize` utility which comes with the `--individual-tensors` option.
+
+- Source code: https://github.com/Thireus/ik_llama.cpp/tree/th/quantize_individual_tensors
+- Builds (macOS, Windows and Linux): https://github.com/Thireus/ik_llama.cpp/releases/tag/th-quantize_individual_tensors-b4210-7a44805
+
+Usage example:
+```
+./llama-quantize --keep-split --imatrix imatrix_ubergarm.dat --individual-tensors 2,3,1094 Kimi-K2-Thinking-THIREUS-BF16-SPECIAL_TENSOR-00001-of-01097.gguf my_new_shards.gguf iq3_s 12
+```
+
+For more information about how to use it: https://github.com/Thireus/GGUF-Tool-Suite/issues/45
+
+You can produce your own quantized shards from Thireus' special BF16 model using `quantize_model.sh` found on https://github.com/Thireus/GGUF-Tool-Suite, for example:
+
+```
+./quantize_model.sh --model "Qwen3.6-122B-A10B" --qtype iq2_xxs
+```
+
+You can disable reasoning (thinking) when using jinja templates for supported models:
+
+```
+llama-server ... --jinja --chat-template-kwargs '{"enable_thinking": false}'
+```
+
+Enjoy optimized quantization! 🎉

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00001-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:976ffdbba9ef4d532b2076208e45a7cd75947e02ce183ccdbe9a0cffe2949d27
+size 10943008

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00002-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27af5ded3b2683a01a3e0d794a9bd2cdea713b357108e924719ba34bc454e226
+size 270172352

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00003-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b37075bda02e43d28a99483929eb99851838b9fe6f58d6ded409baa4e51ec5
+size 142606528

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00004-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a089ae27b0a7641e7d3c041c8c99ee0561bf5138ae3c755fd0b4d10e7f540422
+size 142606528

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00005-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6a82a3e591b967e4b6652b8803b7c75d87666cd1d50fccdd6ac363d2c214dc
+size 270172320

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00006-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99ffa9a42c8779f69e1bddbc6cbdb51d1eaba7a99004b9e12dec94cef23802d
+size 8352

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00007-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b024a0c47240992b7dc7afeaba490b8648c7ad73a46e72c6c1c099f1e2419601
+size 4456640

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00008-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562c312372d40a793a5da965ae12fe1b0eeae98a2a0a391edb0d97483befe5dd
+size 8384

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00009-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159a66b22e54bfd39b3ab613366c6be4eed9a8f183f127cbff73c432dfe4bafe
+size 142606528

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00010-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f5bf0b7ca59bd4e5cc9c4e3009c1e25faca26ba28da67dea0d276e8ca04c7d4
+size 1048768

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00011-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cd686b88b02a2226b4b802127d94581d764c7dcf0eb623afe715180cec0890
+size 557248

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00012-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ec40e33a2a2f0268858cbaf78b3b4cf9073ba592d5434055c31d788621b1a4
+size 557248

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00013-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462c6fed27c7d2bc975ddf9429ef8a47b8df844a4c362b14d2e799803a4aa482
+size 557248

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00014-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98f329aefff68ec4266b9e2a2720abdf99af4259db798889037217d4162041d
+size 4288

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00015-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008df60d61333c9c5917bb6b798d9441611a30b2109e1cb2382c8b026ec2aebe
+size 8384

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00016-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665c6694f97931b081baa3af161ddf592951b65529fc389dfea6a17f72b8694c
+size 1216

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00017-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80c597a21bb7d6ffd6cfbb6ea86a561b61bb474719fc8ec3e620add8ff111db
+size 557248

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00018-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a0485a09b3548b5497665200ab00ea8254c933b4d690b7d11ce58a0a8323ef
+size 4456640

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00019-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207712168da8623f0532a14729455d9bdce4e3cfdfd97e1c4244d95d764c6e71
+size 1216

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00020-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9372e110a50f51a297ef25394240b9fcc23929cf20b69dff14a8b66edba2533d
+size 8913088

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00021-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfe4fdaddd7787bfdcb1a7fb753e8f4b18f98fb8127fc9d0371d791a98fa7f46
+size 557248

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00022-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc194ba2a779fa79285998321f80c90072dd79c0d82753fbbc863213338061e
+size 8384

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00023-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6356be016e3a20fff4d4840d34542fe0e745cf79c3a5625bcb66a0adbc9adedf
+size 8384

mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00024-of-00024.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afcf4bbd7f3a906fc1116b46d1238c5c805a24d60d08b03169541c5696783c3
+size 8384

tensors.map

@@ -0,0 +1,23 @@
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00002-of-00024.gguf:27af5ded3b2683a01a3e0d794a9bd2cdea713b357108e924719ba34bc454e226:token_embd.weight:shape=(2048, 248320):dtype=iq4_xs:elements=508559360:bytes=270172160
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00003-of-00024.gguf:01b37075bda02e43d28a99483929eb99851838b9fe6f58d6ded409baa4e51ec5:blk.40.ffn_gate_exps.weight:shape=(2048, 512, 256):dtype=iq4_xs:elements=268435456:bytes=142606336
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00004-of-00024.gguf:a089ae27b0a7641e7d3c041c8c99ee0561bf5138ae3c755fd0b4d10e7f540422:blk.40.ffn_up_exps.weight:shape=(2048, 512, 256):dtype=iq4_xs:elements=268435456:bytes=142606336
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00005-of-00024.gguf:fe6a82a3e591b967e4b6652b8803b7c75d87666cd1d50fccdd6ac363d2c214dc:output.weight:shape=(2048, 248320):dtype=iq4_xs:elements=508559360:bytes=270172160
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00006-of-00024.gguf:e99ffa9a42c8779f69e1bddbc6cbdb51d1eaba7a99004b9e12dec94cef23802d:output_norm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00007-of-00024.gguf:b024a0c47240992b7dc7afeaba490b8648c7ad73a46e72c6c1c099f1e2419601:blk.40.nextn.eh_proj.weight:shape=(4096, 2048):dtype=iq4_xs:elements=8388608:bytes=4456448
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00008-of-00024.gguf:562c312372d40a793a5da965ae12fe1b0eeae98a2a0a391edb0d97483befe5dd:blk.40.attn_norm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00009-of-00024.gguf:159a66b22e54bfd39b3ab613366c6be4eed9a8f183f127cbff73c432dfe4bafe:blk.40.ffn_down_exps.weight:shape=(512, 2048, 256):dtype=iq4_xs:elements=268435456:bytes=142606336
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00010-of-00024.gguf:7f5bf0b7ca59bd4e5cc9c4e3009c1e25faca26ba28da67dea0d276e8ca04c7d4:blk.40.ffn_gate_inp.weight:shape=(2048, 256):dtype=bf16:elements=524288:bytes=1048576
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00011-of-00024.gguf:86cd686b88b02a2226b4b802127d94581d764c7dcf0eb623afe715180cec0890:blk.40.ffn_down_shexp.weight:shape=(512, 2048):dtype=iq4_xs:elements=1048576:bytes=557056
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00012-of-00024.gguf:48ec40e33a2a2f0268858cbaf78b3b4cf9073ba592d5434055c31d788621b1a4:blk.40.ffn_gate_shexp.weight:shape=(2048, 512):dtype=iq4_xs:elements=1048576:bytes=557056
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00013-of-00024.gguf:462c6fed27c7d2bc975ddf9429ef8a47b8df844a4c362b14d2e799803a4aa482:blk.40.ffn_up_shexp.weight:shape=(2048, 512):dtype=iq4_xs:elements=1048576:bytes=557056
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00014-of-00024.gguf:f98f329aefff68ec4266b9e2a2720abdf99af4259db798889037217d4162041d:blk.40.ffn_gate_inp_shexp.weight:shape=(2048,):dtype=bf16:elements=2048:bytes=4096
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00015-of-00024.gguf:008df60d61333c9c5917bb6b798d9441611a30b2109e1cb2382c8b026ec2aebe:blk.40.post_attention_norm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00016-of-00024.gguf:665c6694f97931b081baa3af161ddf592951b65529fc389dfea6a17f72b8694c:blk.40.attn_k_norm.weight:shape=(256,):dtype=f32:elements=256:bytes=1024
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00017-of-00024.gguf:f80c597a21bb7d6ffd6cfbb6ea86a561b61bb474719fc8ec3e620add8ff111db:blk.40.attn_k.weight:shape=(2048, 512):dtype=iq4_xs:elements=1048576:bytes=557056
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00018-of-00024.gguf:68a0485a09b3548b5497665200ab00ea8254c933b4d690b7d11ce58a0a8323ef:blk.40.attn_output.weight:shape=(4096, 2048):dtype=iq4_xs:elements=8388608:bytes=4456448
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00019-of-00024.gguf:207712168da8623f0532a14729455d9bdce4e3cfdfd97e1c4244d95d764c6e71:blk.40.attn_q_norm.weight:shape=(256,):dtype=f32:elements=256:bytes=1024
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00020-of-00024.gguf:9372e110a50f51a297ef25394240b9fcc23929cf20b69dff14a8b66edba2533d:blk.40.attn_q.weight:shape=(2048, 8192):dtype=iq4_xs:elements=16777216:bytes=8912896
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00021-of-00024.gguf:cfe4fdaddd7787bfdcb1a7fb753e8f4b18f98fb8127fc9d0371d791a98fa7f46:blk.40.attn_v.weight:shape=(2048, 512):dtype=iq4_xs:elements=1048576:bytes=557056
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00022-of-00024.gguf:6fc194ba2a779fa79285998321f80c90072dd79c0d82753fbbc863213338061e:blk.40.nextn.shared_head_norm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00023-of-00024.gguf:6356be016e3a20fff4d4840d34542fe0e745cf79c3a5625bcb66a0adbc9adedf:blk.40.nextn.enorm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192
+mtp-Qwen3.6-35B-A3B-THIREUS-IQ4_XS-SPECIAL_TENSOR-00024-of-00024.gguf:2afcf4bbd7f3a906fc1116b46d1238c5c805a24d60d08b03169541c5696783c3:blk.40.nextn.hnorm.weight:shape=(2048,):dtype=f32:elements=2048:bytes=8192