Chimanwakis/qwen-calculus-sft-GGUF overview
Chimanwakis/qwen calculus sft GGUF GGUF export of the calculus/Manim SFT model. The LoRA adapter was merged into Chimanwakis/qwen manim animation 16bit before …
Runs locally from ~1.80 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| qwen_manim_animation_16bit.Q4_K_M.gguf | GGUF | GGUF | 1.80 GB | Download |
Model Details
| Model ID | Chimanwakis/qwen-calculus-sft-GGUF |
|---|---|
| Author | Chimanwakis |
| Pipeline | text-generation |
| License | — |
| Base model | Chimanwakis/qwen_manim_animation_16bit |
| Last modified | 2026-08-22T20:16:08.000Z |
Model README
---
base_model: Chimanwakis/qwen_manim_animation_16bit
datasets:
- Chimanwakis/calculus_manim
library_name: llama.cpp
pipeline_tag: text-generation
tags:
- gguf
- unsloth
- qwen2.5-coder
- calculus
- manim
---
Chimanwakis/qwen-calculus-sft-GGUF
GGUF export of the calculus/Manim SFT model. The LoRA adapter was merged into
Chimanwakis/qwen_manim_animation_16bit before conversion with Unsloth.
Files
| File | Size |
|---|---:|
| qwen_manim_animation_16bit.Q4_K_M.gguf | 1.80 GiB |
Quantization requested: Q4_K_M. File hashes are available in
SHA256SUMS.
llama.cpp
llama-cli -m qwen_manim_animation_16bit.Q4_K_M.gguf -cnv -c 4096Increase -c only when the computer has enough memory. The original SFT data is
hosted at https://huggingface.co/datasets/Chimanwakis/calculus_manim.
Run Chimanwakis/qwen-calculus-sft-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models