commit 3f49da36ebd350288c1adde8da59be442ac8d457
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Mon May 4 01:33:56 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: kenonix/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k-Q8_0-GGUF
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..873c1bf
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
+llama-3.3-8b-thinking-gemini-flash-11000x-128k-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..7f8961c
--- /dev/null
+++ b/README.md
@@ -0,0 +1,95 @@
+---
+license: apache-2.0
+datasets:
+- TeichAI/gemini-2.5-flash-11000x
+base_model: DavidAU/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- zh
+- ja
+- ru
+- ko
+tags:
+- thinking
+- reasoning
+- Gemini Flash
+- creative
+- creative writing
+- fiction writing
+- plot generation
+- sub-plot generation
+- story generation
+- scene continue
+- storytelling
+- fiction story
+- science fiction
+- romance
+- all genres
+- story
+- writing
+- vivid prosing
+- vivid writing
+- fiction
+- roleplaying
+- bfloat16
+- role play
+- 128k context
+- llama3.3
+- llama-3
+- llama-3.3
+- unsloth
+- finetune
+- llama-cpp
+- gguf-my-repo
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# kenonix/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k-Q8_0-GGUF
+This model was converted to GGUF format from [`DavidAU/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k`](https://huggingface.co/DavidAU/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
+Refer to the [original model card](https://huggingface.co/DavidAU/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k) for more details on the model.
+
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+
+```bash
+brew install llama.cpp
+
+```
+Invoke the llama.cpp server or the CLI.
+
+### CLI:
+```bash
+llama-cli --hf-repo kenonix/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k-Q8_0-GGUF --hf-file llama-3.3-8b-thinking-gemini-flash-11000x-128k-q8_0.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo kenonix/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k-Q8_0-GGUF --hf-file llama-3.3-8b-thinking-gemini-flash-11000x-128k-q8_0.gguf -c 2048
+```
+
+Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+
+Step 1: Clone llama.cpp from GitHub.
+```
+git clone https://github.com/ggerganov/llama.cpp
+```
+
+Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
+```
+cd llama.cpp && LLAMA_CURL=1 make
+```
+
+Step 3: Run inference through the main binary.
+```
+./llama-cli --hf-repo kenonix/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k-Q8_0-GGUF --hf-file llama-3.3-8b-thinking-gemini-flash-11000x-128k-q8_0.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo kenonix/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k-Q8_0-GGUF --hf-file llama-3.3-8b-thinking-gemini-flash-11000x-128k-q8_0.gguf -c 2048
+```
diff --git a/llama-3.3-8b-thinking-gemini-flash-11000x-128k-q8_0.gguf b/llama-3.3-8b-thinking-gemini-flash-11000x-128k-q8_0.gguf
new file mode 100644
index 0000000..7ff04ef
--- /dev/null
+++ b/llama-3.3-8b-thinking-gemini-flash-11000x-128k-q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3937251134c047ed7940cfec228ed0b35acaa2ae94092304d6325006b391be7f
+size 8540771968