mirai-s-ada
mirai-s-ada is Mirai S (Qwen3.8-27B-S trellis GGUF) on a 12 GB RTX 4070: 262k q8_0 tiered cache, MTP drafting at every depth, harness-proofing, the layer; receipts. - professorpalmer/mirai-s-ada. It is ranked #3871 on the AI Radar, in Open & local models, first seen 29 days ago and shared in 10 posts (182.1k views).
GitHub - professorpalmer/mirai-s-ada: Mirai S (Qwen3.8-27B-S trellis GGUF) on a 12 GB RTX 4070: 262k q8_0 tiered cache, MTP drafting at every depth, harness-proofing, the layer; receipts. · GitHub Skip to content Navigation Menu Sign in Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation mirai-s-ada Public Notifications You must be signed in to change notification settings…
What people said about mirai-s-ada on X
My Mirai S patch is, still, the best LLM on a 12GB card of any that I've tested. Insane what @trymirai did with that model, tbh. https://github.com/professorpalmer/mirai-s-ada
— @CaryPalmerr, 7 days ago · 17 likes · see the post
Alternatives to mirai-s-ada
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- unsloth.ai — Guide to running Mistral Large 4 GGUFs locally with Unsloth and llama.cpp.
- niklaslenz.com — Play the world in your browser. Every number, the exact command and the raw output
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
- project-maya — Plus a round of fixes, UI improvements and community PRs.
- twil-8b — Text Generation model with 9B parameters. Download, explore files and run it on Hugging Face.
mirai-s-ada in numbers
- Rank on the AI Radar: #3871 of 10412
- Shared in 10 posts by 3 accounts: @CaryPalmerr
- 182.1k views on those posts
- First seen 29 days ago, last shared 7 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Open & local models
FAQ
What is mirai-s-ada?
Mirai S (Qwen3.8-27B-S trellis GGUF) on a 12 GB RTX 4070: 262k q8_0 tiered cache, MTP drafting at every depth, harness-proofing, the layer; receipts. - professorpalmer/mirai-s-ada It was first shared on X 29 days ago and is ranked #3871 on the AI Radar.
Is mirai-s-ada free?
It is open source.
Who shared mirai-s-ada?
3 accounts on X, including @CaryPalmerr, in 10 posts totalling 182.1k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.5k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:50 UTC. Full method.