Smallest reasoning models for NVIDIA T4 16GB (free Colab)

Verified open reasoning models that fit in 16 GB on NVIDIA T4 16GB (free Colab), smallest first — with license clarity and hosted-download status. Top pick: mradermacher/Phi-4-mini-reasoning-heretic-GGUF (~1.87 GB).

Hugging Bay is intentionally crawlable for search engines, answer engines, user-requested AI fetches, frontier AI assistants, and open-source agents. Public pages describe verified open-source AI artifact metadata, provenance, licenses, community trust signals, and selective hosted mirrors with hashes. Hugging Bay does not bypass gated or restricted upstream access controls.

Machine-readable entrypoints: robots.txt, AI search guidance, well-known AI search JSON, AI citation packs, well-known AI citation JSON, llms.txt, llms-full.txt, AI crawler policy, AI bot allowlist, answer-engine manifest, agent manifest, OpenAPI, and indexing status.

Verified open reasoning models that fit in 16 GB on NVIDIA T4 16GB (free Colab), smallest first — with license clarity and hosted-download status. Top pick: mradermacher/Phi-4-mini-reasoning-heretic-GGUF (~1.87 GB).

#ModelEst. VRAMLicenseCommercialHostingFit page
1mradermacher/Phi-4-mini-reasoning-heretic-GGUF~1.87 GBmityesexternalcheck
2mradermacher/Reasoning-SmolLM2-135M-i1-GGUF~1.87 GBapache-2.0yesexternalcheck
3Multilingual-Multimodal-NLP/IndustrialCoder-Thinking~1.87 GBapache-2.0yesexternalcheck
4mradermacher/SphinX-GGUF~1.87 GBapache-2.0yesexternalcheck
511-47/GPT2.5.5-Awakened.Thinker-0.1B~2.48 GBmityesexternalcheck
6CromIA/think-vetor-0.5b-lora~3.28 GBapache-2.0yesexternalcheck
7AQ-MedAI/Diver-Retriever-0.6B~3.48 GBapache-2.0yesexternalcheck
8Ayansk11/FinSenti-Qwen3-1.7B-GGUF~6.08 GBapache-2.0yesexternalcheck
9mradermacher/DeepBrainz-R1-2B-i1-GGUF~6.68 GBapache-2.0yesexternalcheck
10EphAsad/Atem-Pharaoh-3B~7.74 GBapache-2.0yesexternalcheck

Other GPUs: RTX 4090 24GB · RTX 3090 24GB · RTX 3060 12GB · A100 80GB · H100 80GB · mac-m3-max-64

Other tasks on NVIDIA T4 16GB (free Colab): coding · chat · translation · summarization · vision · audio · rag · agents

Fit = weights + KV-cache estimate under 16 GB. Recomputed hourly from live catalog state.