Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,72 @@
+*.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
+google_gemma-3-12b-it-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-mmproj-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-f16-q8.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-mmproj-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q8.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-mmproj-f32.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-bf16-q8.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+car-1.jpg filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-f16.gguf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-q2_k_s.guuf filter=lfs diff=lfs merge=lfs -text
+google_gemma-3-12b-it-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,264 @@
+---
+license: gemma
+pipeline_tag: image-text-to-text
+tags:
+- gemma
+- vision
+- image
+- llama.cpp
+---
+
+# <span style="color: #7FFF7F;">Gemma-3 12B Instruct GGUF Models</span>
+
+
+## How to Use Gemma 3 Vision with llama.cpp
+
+To utilize the experimental support for Gemma 3 Vision in `llama.cpp`, follow these steps:
+
+1. **Clone the lastest llama.cpp Repository**:
+   ```bash
+   git clone https://github.com/ggml-org/llama.cpp.git
+   cd llama.cpp
+   ```
+
+
+2. **Build the Llama.cpp**:
+
+Build llama.cpp as usual : https://github.com/ggml-org/llama.cpp#building-the-project
+
+Once llama.cpp is built Copy the ./llama.cpp/build/bin/llama-gemma3-cli to a chosen folder.
+
+3. **Download the Gemma 3 gguf file**:
+
+https://huggingface.co/Mungert/gemma-3-12b-it-gguf/tree/main
+
+Choose a gguf file without the mmproj in the name
+
+Example gguf file : https://huggingface.co/Mungert/gemma-3-12b-it-gguf/resolve/main/google_gemma-3-12b-it-q4_k_l.gguf
+
+Copy this file to your chosen folder.
+
+4. **Download the Gemma 3 mmproj file**
+
+https://huggingface.co/Mungert/gemma-3-12b-it-gguf/tree/main
+
+Choose a file with mmproj in the name
+
+Example mmproj file : https://huggingface.co/Mungert/gemma-3-12b-it-gguf/resolve/main/google_gemma-3-12b-it-mmproj-bf16.gguf
+
+Copy this file to your chosen folder.
+
+5. Copy images to the same folder as the gguf files or alter paths appropriately.
+ 
+ In the example below the gguf files, images and llama-gemma-cli are in the same folder.
+
+ Example image:  image https://huggingface.co/Mungert/gemma-3-12b-it-gguf/resolve/main/car-1.jpg
+
+ Copy this file to your chosen folder.
+
+6. **Run the CLI Tool**:
+
+ From your chosen folder :
+ 
+   ```bash
+   llama-gemma3-cli -m google_gemma-3-12b-it-q4_k_l.gguf --mmproj google_gemma-3-12b-it-mmproj-bf16.gguf
+   ```
+
+```
+ Running in chat mode, available commands:
+   /image <path>    load an image
+   /clear           clear the chat history
+   /quit or /exit   exit the program
+
+> /image car-1.jpg
+Encoding image car-1.jpg
+Image encoded in 46305 ms
+Image decoded in 19302 ms
+
+> what is the image of
+Here's a breakdown of what's in the image:
+
+**Subject:** The primary subject is a black Porsche Panamera Turbo driving on a highway.
+
+**Details:**
+
+*   **Car:** It's a sleek, modern Porsche Panamera Turbo, identifiable by its distinctive rear design, the "PORSCHE" lettering, and the "Panamera Turbo" badge. The license plate reads "CVC-911".
+*   **Setting:** The car is on a multi-lane highway, with a blurred background of trees, a distant building, and a cloudy sky. The lighting suggests it's either dusk or dawn.
+*   **Motion:** The image captures the car in motion, with a slight motion blur to convey speed.
+
+**Overall Impression:** The image conveys a sense of speed, luxury, and power. It's a well-composed shot that highlights the car's design and performance.
+
+Do you want me to describe any specific aspect of the image in more detail, or perhaps analyze its composition?
+```
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+
+Please click like ❤️ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com).  
+💬 Click the **chat icon** (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM.  
+
+### What I'm Testing 
+I'm experimenting with **function calling** against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 
+🟡 **TestLLM** – Runs **Phi-4-mini-instruct** using phi-4-mini-q4_0.gguf , llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! .  
+
+### The other Available AI Assistants
+🟢 **TurboLLM** – Uses **gpt-4o-mini** Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM .  
+🔵 **HugLLM** – Runs **open-source Hugging Face models** Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability)  
+
+
+## **Choosing the Right Model Format**  
+
+Selecting the correct model format depends on your **hardware capabilities** and **memory constraints**.  
+
+### **BF16 (Brain Float 16) – Use if BF16 acceleration is available**  
+- A 16-bit floating-point format designed for **faster computation** while retaining good precision.  
+- Provides **similar dynamic range** as FP32 but with **lower memory usage**.  
+- Recommended if your hardware supports **BF16 acceleration** (check your device’s specs).  
+- Ideal for **high-performance inference** with **reduced memory footprint** compared to FP32.  
+
+📌 **Use BF16 if:**  
+✔ Your hardware has native **BF16 support** (e.g., newer GPUs, TPUs).  
+✔ You want **higher precision** while saving memory.  
+✔ You plan to **requantize** the model into another format.  
+
+📌 **Avoid BF16 if:**  
+❌ Your hardware does **not** support BF16 (it may fall back to FP32 and run slower).  
+❌ You need compatibility with older devices that lack BF16 optimization.  
+
+---
+
+### **F16 (Float 16) – More widely supported than BF16**  
+- A 16-bit floating-point **high precision** but with less of range of values than BF16. 
+- Works on most devices with **FP16 acceleration support** (including many GPUs and some CPUs).  
+- Slightly lower numerical precision than BF16 but generally sufficient for inference.  
+
+📌 **Use F16 if:**  
+✔ Your hardware supports **FP16** but **not BF16**.  
+✔ You need a **balance between speed, memory usage, and accuracy**.  
+✔ You are running on a **GPU** or another device optimized for FP16 computations.  
+
+📌 **Avoid F16 if:**  
+❌ Your device lacks **native FP16 support** (it may run slower than expected).  
+❌ You have memory limtations.  
+
+---
+
+### **Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference**  
+Quantization reduces model size and memory usage while maintaining as much accuracy as possible.  
+- **Lower-bit models (Q4_K)** → **Best for minimal memory usage**, may have lower precision.  
+- **Higher-bit models (Q6_K, Q8_0)** → **Better accuracy**, requires more memory.  
+
+📌 **Use Quantized Models if:**  
+✔ You are running inference on a **CPU** and need an optimized model.  
+✔ Your device has **low VRAM** and cannot load full-precision models.  
+✔ You want to reduce **memory footprint** while keeping reasonable accuracy.  
+
+📌 **Avoid Quantized Models if:**  
+❌ You need **maximum accuracy** (full-precision models are better for this).  
+❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).  
+
+---
+
+### **Summary Table: Model Format Selection**  
+
+| Model Format  | Precision  | Memory Usage  | Device Requirements  | Best Use Case  |  
+|--------------|------------|---------------|----------------------|---------------|  
+| **BF16**     | Highest       | High      | BF16-supported GPU/CPUs  | High-speed inference with reduced memory |  
+| **F16**      | High     | High           | FP16-supported devices | GPU inference when BF16 isn’t available |  
+| **Q4_K**     | Low        | Very Low      | CPU or Low-VRAM devices | Best for memory-constrained environments |  
+| **Q6_K**     | Medium Low     | Low      | CPU with more memory | Better accuracy while still being quantized |  
+| **Q8**       | Medium       | Moderate        | CPU or GPU with enough VRAM | Best accuracy among quantized models |  
+
+
+## **Included Files & Details**  
+
+### `google_gemma-3-12b-it-bf16.gguf`  
+- Model weights preserved in **BF16**.  
+- Use this if you want to **requantize** the model into a different format.  
+- Best if your device supports **BF16 acceleration**.  
+
+### `google_gemma-3-12b-it-f16.gguf`  
+- Model weights stored in **F16**.  
+- Use if your device supports **FP16**, especially if BF16 is not available.  
+
+### `google_gemma-3-12b-it-bf16-q8.gguf`  
+- **Output & embeddings** remain in **BF16**.  
+- All other layers quantized to **Q8_0**.  
+- Use if your device supports **BF16** and you want a quantized version.  
+
+### `google_gemma-3-12b-it-f16-q8.gguf`  
+- **Output & embeddings** remain in **F16**.  
+- All other layers quantized to **Q8_0**.    
+
+### `google_gemma-3-12b-it-q4_k_l.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q4_K**.  
+- Good for **CPU inference** with limited memory.  
+
+### `google_gemma-3-12b-it-q4_k_m.gguf`  
+- Similar to Q4_K.  
+- Another option for **low-memory CPU inference**.  
+
+### `google_gemma-3-12b-it-q4_k_s.gguf`  
+- Smallest **Q4_K** variant, using less memory at the cost of accuracy.  
+- Best for **very low-memory setups**.  
+
+### `google_gemma-3-12b-it-q6_k_l.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q6_K** .  
+
+### `google_gemma-3-12b-it-q6_k_m.gguf`  
+- A mid-range **Q6_K** quantized model for balanced performance .  
+- Suitable for **CPU-based inference** with **moderate memory**.  
+
+### `google_gemma-3-12b-it-q8.gguf`  
+- Fully **Q8** quantized model for better accuracy.  
+- Requires **more memory** but offers higher precision.
+
+
+# Gemma 3 model card
+
+**Model Page**: [Gemma](https://ai.google.dev/gemma/docs/core)
+
+**Resources and Technical Documentation**:
+
+* [Gemma 3 Technical Report][g3-tech-report]
+* [Responsible Generative AI Toolkit][rai-toolkit]
+* [Gemma on Kaggle][kaggle-gemma]
+* [Gemma on Vertex Model Garden][vertex-mg-gemma3]
+
+**Terms of Use**: [Terms][terms]
+
+**Authors**: Google DeepMind
+
+## Model Information
+
+Summary description and brief definition of inputs and outputs.
+
+### Description
+
+Gemma is a family of lightweight, state-of-the-art open models from Google,
+built from the same research and technology used to create the Gemini models.
+Gemma 3 models are multimodal, handling text and image input and generating text
+output, with open weights for both pre-trained variants and instruction-tuned
+variants. Gemma 3 has a large, 128K context window, multilingual support in over
+140 languages, and is available in more sizes than previous versions. Gemma 3
+models are well-suited for a variety of text generation and image understanding
+tasks, including question answering, summarization, and reasoning. Their
+relatively small size makes it possible to deploy them in environments with
+limited resources such as laptops, desktops or your own cloud infrastructure,
+democratizing access to state of the art AI models and helping foster innovation
+for everyone.
+
+### Inputs and outputs
+
+-   **Input:**
+    -  Text string, such as a question, a prompt, or a document to be summarized
+    -  Images, normalized to 896 x 896 resolution and encoded to 256 tokens
+       each
+    -  Total input context of 128K tokens for the 4B, 12B, and 27B sizes, and
+       32K tokens for the 1B size
+
+-   **Output:**
+    -   Generated text in response to the input, such as an answer to a
+        question, analysis of image content, or a summary of a document
+    -   Total output context of 8192 tokens

google_gemma-3-12b-it-bf16-q8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3150fa074c3840afd7963ad669f740529ad737b8199a8867bcba938479a24fe3
+size 13453668352

google_gemma-3-12b-it-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1491e21628cd5318eee2fb810bd3fbad6b76cb5f1d8ca03ac62e344a513c4280
+size 23539658496

google_gemma-3-12b-it-f16-q8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e295c862d99575f53362df887e9007f4c6f32cf59508109ee42be2defb489ca4
+size 13453668352

google_gemma-3-12b-it-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8594dde632b726cfd5f6de3dd44819b666234bc0b43c9f5fb86cf19ec5f0e429
+size 4310290432

google_gemma-3-12b-it-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570901ac6e036c6410a41a6a148cabc9ab3920b441c03517849723e60649c5ff
+size 4020539392

google_gemma-3-12b-it-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207f5c239551130a0e3e1d07726476e7a8e536e651c7fec539b71fd3dead5ece
+size 3840090112

google_gemma-3-12b-it-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6380054cb1c27ec380b4c922569e570753d100c90b0c879eb0a3c0ef8d5a5af
+size 5655519232

google_gemma-3-12b-it-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9e28031bbac1a07ae8af1f9c0a3828ef1a4bdc1fbd326b5d4dd72865e36438
+size 5458112512

google_gemma-3-12b-it-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4718da6e7a65e971c149cc8ce1edc06ea8d714ab4c9545f676ff0b60647216
+size 5205962752

google_gemma-3-12b-it-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e5bc7a192d66e5abd576ca81fb73dce6958fae5a4f68d0d5109a827bf72c2f
+size 6886961152

google_gemma-3-12b-it-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc48e90608ced0b545f39615f1c7065f3148a07afe92e24e02e1aa3c980c7914
+size 6550761472

google_gemma-3-12b-it-mmproj-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e5ba81aeddfc99bac8325a05f173b5f7024d447a1e3a21f40b265bdc0fe26f
+size 854200224

google_gemma-3-12b-it-mmproj-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c02d056410848227001830866e0a269fcc28aaf8ca971bded494003de9f5a5
+size 854200224

google_gemma-3-12b-it-mmproj-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d45f67b21a6718c2f418962ae2c9823ab0b6264ec9d4bad586f173143b8d17b6
+size 1685188512

google_gemma-3-12b-it-mmproj-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd46cb64556fbd4118a944b5b27a8398c5e7b6111957dd0ca7eda472fd0e1f81
+size 590179104

google_gemma-3-12b-it-q2_k_s.guuf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2e6d9a130bbec01e73ac79968f2725032e1c35a4739cc81a3e61f71c9e252e
+size 4448407552

google_gemma-3-12b-it-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223c9d42291e15cccd93871d534b8fd842d9fe821417983b17e1c76f9d026b0b
+size 6008614912

google_gemma-3-12b-it-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139263cfc1a8f13e305f9df2475fe9a85a17e5d54a54cc8e64a8bca091659274
+size 5458112512

google_gemma-3-12b-it-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d067ff720a59326f63b2ee5d6b416c029e0f09f436b6ff4e9825629c09e484
+size 7130755072

google_gemma-3-12b-it-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f715066755a839b2a4dcaf0c33ed812b10d8ab7fc1fbea3c937cb71f4e3fa1
+size 7803154432

google_gemma-3-12b-it-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db0ccbe6e12e3b5ab7f3c23c4dc290d06f2cf2987cca4cc83a0f67e4dc7ded2
+size 7300575232

google_gemma-3-12b-it-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e7dabc065cf9d2096601c23e8986976dceec29bba478c27afe064dd8b83bf1
+size 6935130112

google_gemma-3-12b-it-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10fa539214cbbca169c5264f08fafe944625f41ba0a4c49ee8f25fb2b0a4c7b9
+size 8444833792

google_gemma-3-12b-it-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426e15f8063333a47d8b9419a408b3160f548d36286b2595a6ee6d50ac90117b
+size 8231759872

google_gemma-3-12b-it-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795df22e08ebe7e99b91c19203c5fa5dbfc021f0d1f46d008f99a859efb15ef3
+size 9660608512

google_gemma-3-12b-it-q8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67773ea1deafd3d43df4052a7b19220987edd9817bb3b0f17001586b75a38abd
+size 12509949696

google_gemma-3-12b-it-tq1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19217da4f71089754ca56b2755ad1d8037a690f1fa6d9ab37418189195bb1b5c
+size 3104714752

google_gemma-3-12b-it-tq2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad2f2aaa4f599829583995cd2d9a671e672667dc08e5c3bb58dc625b901dd45
+size 3609014272