TokenAssemble

Local AI workflow

Local agent stack

An agent harness with a locally served model behind it — autonomy without an API bill. The stack: Hermes Agent, Goose, OpenClaw with Ollama serving 3 recommended local models — hardware readiness graded by the same engine as the feasibility checker.

Tools in this category most commonly run against cloud APIs; a local model served by the runtime below is the private, offline option this page sizes.

The stack

Hardware readiness

Each cell is the engine's verdict for the best clean quant of that model on Ollama at 16K context — the same math as the checker, tiers not numbers.

Hardwaregpt-oss-20bqwen3-32bllama-3.3-70b-instruct
NVIDIA GeForce RTX 4090Fits · A+ · MXFP4interactivebetaTight · C · Q4_K_Musable · offloadbetaTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 5090Fits · A+ · MXFP4interactivebetaFits · B · Q4_K_MinteractiveTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 4080Fits · B · MXFP4interactivebetaTight · C · Q4_K_Musable · offloadbetaTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4070Tight · C · MXFP4interactive · offloadbetaTight · C · Q4_K_Musable · offloadbetaTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4060Tight · C · MXFP4interactive · offloadbetaTight · C · Q4_K_Mpainful · offloadbetaTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3090Fits · A+ · MXFP4interactivebetaTight · C · Q4_K_Musable · offloadbetaTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3060 12 GBTight · C · MXFP4interactive · offloadbetaTight · C · Q4_K_Mpainful · offloadbetaTight · C · Q4_K_Mpainful · offloadbeta
AMD Radeon RX 7900 XTXFits · A+ · MXFP4interactivebetaTight · C · Q4_K_Musable · offloadbetaTight · C · Q4_K_Mpainful · offloadbeta
Intel Arc B580Tight · C · MXFP4interactive · offloadbetaTight · C · Q4_K_Mpainful · offloadbetaTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA DGX SparkFits · A+ · MXFP4interactivebetaFits · A+ · Q8_0painfulbetaFits · B · Q8_0painfulbeta
Mac mini M4 24GBFits · B · MXFP4usablebetaWon't fitWon't fit
Mac Studio M3 Ultra 96GBFits · A+ · MXFP4interactivebetaFits · A+ · Q8_0usableFits · B · Q5_K_Musable
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBFits · A+ · MXFP4interactivebetaFits · A+ · Q8_0painfulbetaFits · B · Q8_0painfulbeta

Different hardware? Check your exact machine against any model in this stack.

Check your machine →Don't have the hardware? Build a stack for your budget →

Template picks are editorial; every verdict, grade and tier above comes from the engine over sourced data — how the math works.