Super-squash history to reclaim storage

Co-authored-by: johnbridges <johnbridges@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,78 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+SmallThinker-21BA3B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-iq4_nl.gguf.tmp filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-21BA3B-Instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,230 @@
+---
+language:
+- en
+library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- moe
+---
+
+# <span style="color: #7FFF7F;">SmallThinker-21BA3B-Instruct GGUF Models</span>
+
+
+## <span style="color: #7F7FFF;">Model Generation Details</span>
+
+This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`4cb208c9`](https://github.com/ggerganov/llama.cpp/commit/4cb208c93c1c938591a5b40354e2a6f9b94489bc).
+
+
+
+
+
+---
+
+## <span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>
+
+I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.
+
+In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here:  
+👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py)
+
+While this does increase model file size, it significantly improves precision for a given quantization level.
+
+### **I'd love your feedback—have you tried this? How does it perform for you?**
+
+
+
+
+---
+
+<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
+  Click here to get info on choosing the right GGUF model format
+</a>
+
+---
+
+
+
+<!--Begin Original Model Card-->
+
+
+## Introduction
+
+<p align="center">
+       &nbsp&nbsp🤗 <a href="https://huggingface.co/PowerInfer">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/organization/PowerInfer">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://github.com/SJTU-IPADS/SmallThinker/blob/main/smallthinker-technical-report.pdf">Technical Report</a> &nbsp&nbsp
+       &nbsp&nbsp 📚 <a href="https://huggingface.co/papers/2507.20984">Paper</a> &nbsp&nbsp | &nbsp&nbsp 💻 <a href="https://github.com/SJTU-IPADS/SmallThinker">GitHub Repo</a> &nbsp&nbsp
+</p>
+
+SmallThinker is a family of **on-device native** Mixture-of-Experts (MoE) language models specially designed for local deployment,
+co-developed by the **IPADS** and **School of AI at Shanghai Jiao Tong University** and **Zenergize AI**.
+Designed from the ground up for resource-constrained environments,
+SmallThinker brings powerful, private, and low-latency AI directly to your personal devices,
+without relying on the cloud.
+
+## Paper
+
+The model was presented in the paper [SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment](https://huggingface.co/papers/2507.20984).
+
+### Abstract
+
+While frontier large language models (LLMs) continue to push capability boundaries, their deployment remains confined to GPU-powered cloud infrastructure. We challenge this paradigm with SmallThinker, a family of LLMs natively designed - not adapted - for the unique constraints of local devices: weak computational power, limited memory, and slow storage. Unlike traditional approaches that mainly compress existing models built for clouds, we architect SmallThinker from the ground up to thrive within these limitations. Our innovation lies in a deployment-aware architecture that transforms constraints into design principles. First, We introduce a two-level sparse structure combining fine-grained Mixture-of-Experts (MoE) with sparse feed-forward networks, drastically reducing computational demands without sacrificing model capacity. Second, to conquer the I/O bottleneck of slow storage, we design a pre-attention router that enables our co-designed inference engine to prefetch expert parameters from storage while computing attention, effectively hiding storage latency that would otherwise cripple on-device inference. Third, for memory efficiency, we utilize NoPE-RoPE hybrid sparse attention mechanism to slash KV cache requirements. We release SmallThinker-4B-A0.6B and SmallThinker-21B-A3B, which achieve state-of-the-art performance scores and even outperform larger LLMs. Remarkably, our co-designed system mostly eliminates the need for expensive GPU hardware: with Q4_0 quantization, both models exceed 20 tokens/s on ordinary consumer CPUs, while consuming only 1GB and 8GB of memory respectively. SmallThinker is publicly available at this http URL and this http URL .
+
+## Performance
+
+Note: The model is trained mainly on English.
+
+| Model | MMLU | GPQA-diamond | MATH-500 | IFEVAL | LIVEBENCH | HUMANEVAL | Average |
+|---|---|---|---|---|---|---|---|
+| **SmallThinker-21BA3B-Instruct** | 84.43 | <u>55.05</u> | 82.4 | **85.77** | **60.3** | <u>89.63</u> | **76.26** |
+| Gemma3-12b-it | 78.52 | 34.85 | 82.4 | 74.68 | 44.5 | 82.93 | 66.31 |
+| Qwen3-14B | <u>84.82</u> | 50 | **84.6** | <u>85.21</u>| <u>59.5</u> | 88.41 | <u>75.42</u> |
+| Qwen3-30BA3B | **85.1** | 44.4 | <u>84.4</u> | 84.29 | 58.8 | **90.24** | 74.54 |
+| Qwen3-8B | 81.79 | 38.89 | 81.6 | 83.92 | 49.5 | 85.9 | 70.26 |
+| Phi-4-14B | 84.58 | **55.45** | 80.2 | 63.22 | 42.4 | 87.2 | 68.84 |
+
+For the MMLU evaluation, we use a 0-shot CoT setting.
+
+All models are evaluated in non-thinking mode.
+
+## Speed
+| Model | Memory(GiB) | i9 14900 | 1+13 8ge4 | rk3588 (16G) | Raspberry PI 5 |
+|---|---|---|---|---|---|
+| SmallThinker 21B+sparse | 11.47 | 30.19 | 23.03 | 10.84 | 6.61 |
+| SmallThinker 21B+sparse+limited memory | limit 8G | 20.30 | 15.50 | 8.56 | - |
+| Qwen3 30B A3B | 16.20 | 33.52 | 20.18 | 9.07 | - |
+| Qwen3 30B A3B+limited memory | limit 8G | 10.11 | 0.18 | 6.32 | - |
+| Gemma 3n E2B | 1G, theoretically | 36.88 | 27.06 | 12.50 | 6.66 |
+| Gemma 3n E4B | 2G, theoretically | 21.93 | 16.58 | 7.37 | 4.01 |
+
+Note: i9 14900, 1+13 8ge4 use 4 threads, others use the number of threads that can achieve the maximum speed. All models here have been quantized to q4_0.
+You can deploy SmallThinker with offloading support using [PowerInfer](https://github.com/SJTU-IPADS/PowerInfer/tree/main/smallthinker)
+
+## Model Card
+
+<div align="center">
+
+| **Architecture** | Mixture-of-Experts (MoE) |
+|:---:|:---:|
+| **Total Parameters** | 21B |
+| **Activated Parameters** | 3B |
+| **Number of Layers** | 52 |
+| **Attention Hidden Dimension** | 2560 |
+| **MoE Hidden Dimension** (per Expert) | 768 |
+| **Number of Attention Heads** | 28 |
+| **Number of KV Heads** | 4 |
+| **Number of Experts** | 64 |
+| **Selected Experts per Token** | 6 |
+| **Vocabulary Size** | 151,936 |
+| **Context Length** | 16K |
+| **Attention Mechanism** | GQA |
+| **Activation Function** | ReGLU |
+</div>
+
+## How to Run
+
+### Transformers
+
+`transformers==4.53.3` is required, we are actively working to support the latest version.
+The following contains a code snippet illustrating how to use the model generate content based on given inputs.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+path = "PowerInfer/SmallThinker-21BA3B-Instruct"
+device = "cuda"
+
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.bfloat16, device_map=device, trust_remote_code=True)
+
+messages = [
+    {"role": "user", "content": "Give me a short introduction to large language model."},
+]
+model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(device)
+
+model_outputs = model.generate(
+    model_inputs,
+    do_sample=True,
+    max_new_tokens=1024
+)
+
+output_token_ids = [
+    model_outputs[i][len(model_inputs[i]):] for i in range(len(model_inputs))
+]
+
+responses = tokenizer.batch_decode(output_token_ids, skip_special_tokens=True)[0]
+print(responses)
+
+```
+
+### ModelScope
+
+`ModelScope` adopts Python API similar to (though not entirely identical to) `Transformers`. For basic usage, simply modify the first line of the above code as follows:
+
+```python
+from modelscope import AutoModelForCausalLM, AutoTokenizer
+```
+
+## Statement
+- Due to the constraints of its model size and the limitations of its training data, its responses may contain factual inaccuracies, biases, or outdated information.
+- Users bear full responsibility for independently evaluating and verifying the accuracy and appropriateness of all generated content.
+- SmallThinker does not possess genuine comprehension or consciousness and cannot express personal opinions or value judgments.
+
+<!--End Original Model Card-->
+
+---
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+
+Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:  
+
+👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  
+
+
+The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)
+
+💬 **How to test**:  
+ Choose an **AI assistant type**:  
+   - `TurboLLM` (GPT-4.1-mini)  
+   - `HugLLM` (Hugginface Open-source models)  
+   - `TestLLM` (Experimental CPU-only)  
+
+### **What I’m Testing**  
+I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  
+- **Function calling** against live network services  
+- **How small can a model go** while still handling:  
+  - Automated **Nmap security scans**  
+  - **Quantum-readiness checks**  
+  - **Network Monitoring tasks**  
+
+🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):  
+- ✅ **Zero-configuration setup**  
+- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.
+- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  
+
+### **Other Assistants**  
+🟢 **TurboLLM** – Uses **gpt-4.1-mini** :
+- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. 
+- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
+- **Real-time network diagnostics and monitoring**
+- **Security Audits**
+- **Penetration testing** (Nmap/Metasploit)  
+
+🔵 **HugLLM** – Latest Open-source models:  
+- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
+
+### 💡 **Example commands you could test**:  
+1. `"Give me info on my websites SSL certificate"`  
+2. `"Check if my server is using quantum safe encyption for communication"`  
+3. `"Run a comprehensive security audit on my server"`
+4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution!
+
+### Final Word
+
+I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
+
+If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
+
+I'm also open to job opportunities or sponsorship.
+
+Thank you! 😊

SmallThinker-21BA3B-Instruct-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ff93b54550646202e388325952d2469358598983d23ae3d483d79b7db9b36c
+size 43036667296

SmallThinker-21BA3B-Instruct-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bed1ae457e80b43cc63dc8a0ad39b485740db6aa3fdfa8e19005c6cea24df50
+size 24122977696

SmallThinker-21BA3B-Instruct-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f6385cecb71be1cd4d6ddf0a0062c04670faf545ff7e68189d462a1ba6b5ce
+size 24122977696

SmallThinker-21BA3B-Instruct-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9e3b6b538385e47cb159925917c018e038d7822c3aa02512ad117a0231d1f1
+size 81359936

SmallThinker-21BA3B-Instruct-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8470af0a6e5c87821426f8820e6907d0cbcf5f650f9b11dd97b542068caa8d0e
+size 6207545088

SmallThinker-21BA3B-Instruct-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d96464a74e37bbdd32c33c4896a276fffcc69a1c6dae8e415443464fe9953e
+size 5696098048

SmallThinker-21BA3B-Instruct-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81e1d90d86dfc2ba6b884af1f5c415378b9c05d9fc5ccc9349c01d2270d8547
+size 7839555328

SmallThinker-21BA3B-Instruct-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a16dfb16a4a472d5d991d70bd73681a50470de60dcbc85bc7e1afa2a8d15ce
+size 7475830528

SmallThinker-21BA3B-Instruct-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6262191310193cf6af1679838ab63b8f480d4c1773a4cdd40b98763c400966
+size 6954655488

SmallThinker-21BA3B-Instruct-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0872a1676313500f21ac111e2f83e3b5f735f977e793b339610d11a5aa713973
+size 6513987328

SmallThinker-21BA3B-Instruct-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff4d247b988502cedec2430ef21b7378f69e64477f8cdd965108b4b715f8123
+size 10263138048

SmallThinker-21BA3B-Instruct-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a92219827c433656ef9ea8937a46e1f9ab2e160d4f382f2d4839d1f8674ddc43
+size 9155784448

SmallThinker-21BA3B-Instruct-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e00c5e82fd8ea6707195dc622a140e5e2620746e4626838fe890a2f1c32967
+size 9109909248

SmallThinker-21BA3B-Instruct-iq4_nl.gguf.tmp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5b1e2cb074c517fc42820070d202d80e9e1940af3937907d12b3b3da746544
+size 555799808

SmallThinker-21BA3B-Instruct-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7efd5dedceff4ca92edb73ffacda989b19c2ddd9efd01632408d6b6508a02832
+size 11584894208

SmallThinker-21BA3B-Instruct-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3eb543b3556a0c05589feecc63f4b3b082886de5f452f8d469679502e46180
+size 8206920448

SmallThinker-21BA3B-Instruct-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea85992655b03632ad464a3f582cc6e127ec781cbddd3375e5dbc711537b77b1
+size 8166600448

SmallThinker-21BA3B-Instruct-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f7ba93ac2136d94d9adc372abd0b8fac715914c2f09df5c8934df2d9e9ffb5
+size 10877963008

SmallThinker-21BA3B-Instruct-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9083daaf01358bbab58b05761aa2a1e22ceabded0c16211fa9fb195ba957995
+size 10715664128

SmallThinker-21BA3B-Instruct-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59545815ee6a5ff7fe324434a0dd2fb6b0c8f72e1d9aa6fb4335d0d8436b8074
+size 12133617408

SmallThinker-21BA3B-Instruct-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80910158c2bec5e138bccafb4ecadbbb82b23258a92fee8f335a521b1c6607db
+size 13477228288

SmallThinker-21BA3B-Instruct-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94e598f681a23f089f80a996f1541cbaa15cb185f19d3862ae1c7a9a9fb0467
+size 13577657088

SmallThinker-21BA3B-Instruct-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed83a9fcbac5d853485bfb4d5c8c7efcb5b47aaaa0b938772f95e5175f5085fc
+size 12916132608

SmallThinker-21BA3B-Instruct-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828e9518a9d5ffe24bf4d81ea96bd68dcfc02ad1f48f597951cd2016655b55e6
+size 14820839168

SmallThinker-21BA3B-Instruct-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ccadc107f9357f8b449c444226bd8b0946c3c25b49f1e04389b2eba2e783ff
+size 16164450048

SmallThinker-21BA3B-Instruct-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efce61b0c230d27319c9da6e959d3315594763112ff9c6815a9261006ce22e5
+size 15778888448

SmallThinker-21BA3B-Instruct-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9cb49288ca670b8a1c01c36d9712759c732fa886917e8a57b4164de0ee720f
+size 15542487808

SmallThinker-21BA3B-Instruct-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df58436a58d2c0d5f73b89ed333b68528a2e74769af8a24a90746990215a67b4
+size 17676012288

SmallThinker-21BA3B-Instruct-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be1a351ec0232701824fef718c1b6382206fa5d2425562c6c36b7903f661521
+size 22882504096