metadata
license: apache-2.0
language:
- en
base_model:
- prithivMLmods/Pyxidis-Manim-CodeGen-1.7B
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
Pyxidis-Manim-CodeGen-1.7B-GGUF
Pyxidis-Manim-CodeGen-1.7B is an experimental math animation coding model fine-tuned on Qwen/Qwen3-1.7B using Manim-CodeGen code traces. It is specialized for Python-based mathematical animations with Manim, making it ideal for educators, researchers, and developers working on math visualization and animation pipelines.
Model Files
| File Name | Quant Type | File Size |
|---|---|---|
| Pyxidis-Manim-CodeGen-1.7B.BF16.gguf | BF16 | 3.45 GB |
| Pyxidis-Manim-CodeGen-1.7B.F16.gguf | F16 | 3.45 GB |
| Pyxidis-Manim-CodeGen-1.7B.F32.gguf | F32 | 6.89 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q2_K.gguf | Q2_K | 778 MB |
| Pyxidis-Manim-CodeGen-1.7B.Q3_K_L.gguf | Q3_K_L | 1 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q3_K_M.gguf | Q3_K_M | 940 MB |
| Pyxidis-Manim-CodeGen-1.7B.Q3_K_S.gguf | Q3_K_S | 867 MB |
| Pyxidis-Manim-CodeGen-1.7B.Q4_0.gguf | Q4_0 | 1.05 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q4_1.gguf | Q4_1 | 1.14 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q4_K.gguf | Q4_K | 1.11 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q4_K_M.gguf | Q4_K_M | 1.11 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q4_K_S.gguf | Q4_K_S | 1.06 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q5_0.gguf | Q5_0 | 1.23 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q5_1.gguf | Q5_1 | 1.32 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q5_K.gguf | Q5_K | 1.26 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q5_K_M.gguf | Q5_K_M | 1.26 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q5_K_S.gguf | Q5_K_S | 1.23 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q6_K.gguf | Q6_K | 1.42 GB |
| Pyxidis-Manim-CodeGen-1.7B.Q8_0.gguf | Q8_0 | 1.83 GB |
Quants Usage
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
