Smallest writing models for A100 80GB

Verified open writing models that fit in 80 GB on A100 80GB, smallest first — with license clarity and hosted-download status. Top pick: Local-Novel-LLM-project/WabiSabi-V1.5-beta-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 writing models that fit in 80 GB on A100 80GB, smallest first — with license clarity and hosted-download status. Top pick: Local-Novel-LLM-project/WabiSabi-V1.5-beta-GGUF (~1.87 GB).

#ModelEst. VRAMLicenseCommercialHostingFit page
1Local-Novel-LLM-project/WabiSabi-V1.5-beta-GGUF~1.87 GBapache-2.0yesexternalcheck
2mradermacher/LFM2.5-1.2B-Thinking-Polaris-Heretic-Uncensored-DISTILL-GGUF~2.94 GBapache-2.0yesexternalcheck
3mradermacher/Qwen3-4B-Fiction-On-Fire-Series-6-Model-1002-GGUF~4.07 GBapache-2.0yesexternalcheck
4DavidAU/DarkSapling-V2-Ultra-Quality-7B-GGUF~4.18 GBapache-2.0yesexternalcheck
5TheDrunkenSnail/EVA-Qwen2.5-7B-v0.0-Q4_K_M-GGUF~5.86 GBapache-2.0yesexternalcheck
6DavidAU/L3-Dark-Planet-8B-V2-Eight-Orbs-Of-Power-GGUF~6.27 GBapache-2.0yesexternalcheck
7samunder12/llama-3.1-8b-OneLastStory-gguf~6.43 GBapache-2.0yesexternalcheck
8mradermacher/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking-GGUF~7.09 GBapache-2.0yesexternalcheck
9mradermacher/gemma-3-12b-it-GLM-Flash-4.7-Heretic-Thinking-Uncensored-GRANDE-GGUF~8.74 GBapache-2.0yesexternalcheck
10mradermacher/Sparkle-12B-GGUF~8.74 GBapache-2.0yesexternalcheck

Other GPUs: RTX 4090 24GB · RTX 3090 24GB · RTX 3060 12GB · NVIDIA T4 16GB (free Colab) · H100 80GB · mac-m3-max-64

Other tasks on A100 80GB: coding · chat · reasoning · translation · summarization · vision · audio · rag

Fit = weights + KV-cache estimate under 80 GB. Recomputed hourly from live catalog state.