Every Model That Can Be Run On 10-16GB VRAM Ranked
It's been 4 years since c.ai first hallucination model, and yet, we're nowhere good enough at LLMs in terms of spontaneity/interesting hallucination features.
Proof1 community thread
Key points
- Fortunately, last year brought new architecture that allow those within 10-16GB VRAM range to run something usable up to 64k Context Windows via Kobold or LLAMA.
- Requirements: 10-16GB VRAM - 26-32GB RAM.
- Instruction/Engineering: I've tested WITH and WITHOUT Pandora Instructions, if a model can handle 23 intertwined rules it can handle anything/not need a prompt at all.
- The Catch: I've done a small knowledge test involving animes/manga/movies/music on 70B, 120B and 300B models and found out only models above 200B actually have this sort of data, even a 120B will rarely have the information about the media you're interest at.
Sources (1)
- [1]Every Model That Can Be Run On 10-16GB VRAM Rankedr/LocalLLaMA (top, daily) · Oct 11, 07:12 PM
It's been 4 years since c.ai first hallucination model, and yet, we're nowhere good enough at LLMs in terms of spontaneity/interesting hallucination features.
Fortunately, last year brought new architecture that allow those within 10-16GB VRAM range to run something usable up to 64k Context Windows via Kobold or LLAMA.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution
- Oct 9, 2026Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs
- Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
- Oct 9, 2026Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
- Oct 8, 2026Text is so 2023
- Oct 8, 2026Google brings agentic AI to Gemini, starting with businesses