Uncensored 26.4B Inkling 2 Mini runs locally on a 12GB laptop, keeps 98% MMLU
udmrzn · x · 2026-11-22
AtomicChat released uncensored GGUF quantizations of Inkling 2 Mini (26.4B), in three sizes from 8.67 to 16.53GB, runnable locally on a 12GB laptop.
In their tests refusals dropped from 100% to 0% while retaining about 98% of the original MMLU accuracy. Quants are available on Hugging Face.
Related event: Uncensored 26.4B Inkling 2 Mini runs locally on 12GB laptops(2 posts)→
More from Infra
- Metal NVFP4/MXFP8 Kernels Cut Inkling 2 Mini Memory from 46.2GiB to 9.9GiB on M3 Max — GabGarrett · 2026-11-22
- Training compute cost per task may be mere cents, argues 1a3orn — if models generalize from small runs — 1a3orn · 2026-11-22
- Miners 'hacked' Chutes for a year with millions in incentives to forge real end-to-end TEE privacy — const_reborn · 2026-11-22
- lxask: a fine-tuned 1.5B model turns plain English into offline Linux commands, self-checked against man pages — Arch-r007 · 2026-11-22
- Second OpenRouter Leak in a Month: MiniMax-Route Prompts May Have Been Read — const_reborn · 2026-11-22
- capy-flash v0.16 runs Inkling 2 Mini on two 16GB GPUs at 149 tok/s with 254k context in NVFP4 — FeydRowan · 2026-11-22