Downloads · 30 days
65
23% of all-time downloads
AOS-gemma4-manim-gguf
nabin2004/AOS-gemma4-manim-gguf
AOS-gemma4-manim-gguf is a text generation model from nabin2004. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
Q4KM GGUF of the AOS Manim SFT merged model. Drop-in for Ollama and llama.cpp.
All-time downloads
277
Public
Repo size
3.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf3.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Access
- Public
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026
- SHA
- dbecfe22
Try a prompt
Base models
Model card
From the Hugging Face model README
AOS Gemma 4 Manim SFT (GGUF)
Q4_K_M GGUF of the AOS Manim SFT merged model. Drop-in for Ollama and llama.cpp.
Model URL: https://huggingface.co/nabin2004/AOS-gemma4-manim-gguf
Files
| File | Description |
|---|---|
aos-gemma4-manim-Q4_K_M.gguf | Quantized weights (~2 GB for E2B) |
Modelfile | Ollama import template |
Related repos
| Artifact | Repo |
|---|---|
| LoRA adapter | nabin2004/AOS-gemma4-manim-sft |
| Merged HF weights | nabin2004/AOS-gemma4-manim-merged |
Ollama
Pull from Hugging Face or create locally from the downloaded GGUF:
ollama create aos-gemma4-manim -f Modelfile
ollama run aos-gemma4-manim
Requires Ollama 0.30+ (native Gemma 4 support).
OpenAI-compatible API
Ollama exposes /v1/chat/completions on port 11434:
from gemma4_client import DEFAULT_OLLAMA_BASE_URL, Gemma4Client
client = Gemma4Client(
model="aos-gemma4-manim",
base_url=DEFAULT_OLLAMA_BASE_URL,
api_key="ollama",
)
print(client.chat("Animate a unit circle morphing into an ellipse."))
llama.cpp
./llama-server -m aos-gemma4-manim-Q4_K_M.gguf --chat-template gemma --port 8080
How this was produced
cd apps/sft
export LLAMA_CPP_DIR=~/llama.cpp
uv run python export_gguf.py \
--model-dir ./gemma4-manim-merged \
--output-dir ./gemma4-manim-gguf \
--push-to-hub
Quantization chain: merge_adapter.py → convert_hf_to_gguf.py (F16) → llama-quantize Q4_K_M.
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Languages
- en
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026