Shawon Ashraf's picture

Shawon Ashraf

shawon

·

https://rashomon-gh.github.io

AI & ML interests

Multi-Modal ML, Learning Dynamics in Larger Models, XAI

Recent Activity

reacted to ovi054's post with ❤️ 1 day ago

Qwen3-14B Manim Expert LoRA For "Build Small Hackathon", I built a Gradio app that turns any concept into a Manim explainer video. This is powered by Qwen3-14B + Manim LoRA I trained on a synthetic 10k dataset I generated. 👉 Try it now: https://huggingface.co/spaces/build-small-hackathon/anim-vid-ai

liked a model 1 day ago

moonshotai/Kimi-K2.7-Code

liked a model 1 day ago

lordx64/Qwable-v1

View all activity

Organizations

shawon 's models 29

shawon/Qwen3.6-35B-A3B-mlx-2Bit

Image-Text-to-Text • 35B • Updated 15 days ago • 184

shawon/Qwen3.6-35B-A3B-mlx-4Bit

Image-Text-to-Text • 35B • Updated 15 days ago • 140

shawon/Qwen3.6-35B-A3B-mlx-8Bit

Image-Text-to-Text • 35B • Updated 15 days ago • 113

shawon/gemma-4-26B-A4B-it-mlx-8Bit

Image-Text-to-Text • 25B • Updated May 12 • 25

shawon/gemma-4-26B-A4B-mlx-8Bit

Image-Text-to-Text • 25B • Updated May 12 • 45

shawon/gpt-oss-120b-mlx-4Bit

Text Generation • 117B • Updated May 11 • 699 • 1

shawon/gpt-oss-120b-mlx-8Bit

Text Generation • 117B • Updated May 11 • 383 • 1

shawon/gemma-4-31B-it-mlx-8Bit

Image-Text-to-Text • 31B • Updated May 11 • 16

shawon/Llama-3.3-70B-Instruct-mlx-4Bit

Text Generation • 71B • Updated May 6 • 413 • 1

shawon/Llama-3.3-70B-Instruct-mlx-8Bit

Text Generation • 71B • Updated May 6 • 152

shawon/GLM-4.7-Flash-16bit

Text Generation • 31B • Updated Mar 11 • 8

shawon/Qwen3.5-4B-16bit

Image-Text-to-Text • 5B • Updated Mar 10 • 2

shawon/deepseek_ocr_f16

Image Feature Extraction • 3B • Updated Nov 12, 2025 • 4

shawon/Qwen3_14B_16bit-mlx-8Bit

Text Generation • 15B • Updated Oct 17, 2025 • 17

shawon/orpheus_3B_tts_16bit-mlx-4Bit

Text Generation • 0.5B • Updated Oct 17, 2025 • 29

shawon/orpheus_3B_tts_16bit

Text Generation • 3B • Updated Oct 17, 2025 • 1

shawon/llama3.1_8B_16bit-mlx-8Bit

Text Generation • 8B • Updated Oct 14, 2025 • 2

shawon/llama3.1_8B_16bit-mlx-4Bit

Text Generation • 1B • Updated Oct 14, 2025 • 3

shawon/gpt-oss-20B-mxfp4-mlx-4Bit

Text Generation • 21B • Updated Oct 14, 2025 • 16

shawon/gemma-3N-finetune-mlx-4Bit

Image-Text-to-Text • 1B • Updated Oct 14, 2025 • 8

shawon/Qwen3_14B_16bit-mlx-4Bit

Text Generation • 15B • Updated Oct 14, 2025 • 28

shawon/Qwen3_14B_16bit-Q8_0-GGUF

15B • Updated Oct 10, 2025 • 20

shawon/Qwen3_14B_16bit-Q4_K_M-GGUF

15B • Updated Oct 10, 2025 • 13

shawon/Qwen3_14B_16bit

Text Generation • 15B • Updated Oct 10, 2025 • 1

shawon/llama3.1_8B_16bit-Q4_K_M-GGUF

8B • Updated Oct 10, 2025 • 5

shawon/llama3.1_8B_16bit

Text Generation • 8B • Updated Oct 8, 2025

shawon/gemma-3N-finetune-Q4_K_M-GGUF

7B • Updated Oct 7, 2025 • 4

shawon/gemma-3N-finetune

8B • Updated Oct 6, 2025 • 3

shawon/gpt-oss-20B-mxfp4

Text Generation • 22B • Updated Oct 5, 2025 • 1