MODELINDEX

Which model works best on your machine?

The first benchmark measured across Model × Quant × Hardware × Speed × Quality — signed and verifiable.

World's First Consumer Hardware AI Benchmark

offline

preview

Model			Hardware Profile				Performance
Rank	Model	Quant	OS	Processor	RAM	GPU	Score	tok/s	Gate%	Installs
01	Qwen3-80B-A3B	Q6_K	macOS	Apple M4 Max	128 GB	Apple GPU	91	41.5	98%	1,104
02	Phi-4-14B	Q4_K_M	macOS	Apple M3	16 GB	Apple GPU	91	95.2	86%	2,410
03	Qwen3-80B-A3B	Q4_K_M	Windows	Intel Core Ultra 9	128 GB	NVIDIA RTX 4090	89	71.2	97%	432
04	Qwen3-30B	Q5_K_M	macOS	Apple M4 Pro	32 GB	Apple GPU	88	62.4	94%	1,820
05	Qwen3-80B-A3B	Q4_K_M	macOS	Apple M4 Max	128 GB	Apple GPU	87	56	97%	2,341
06	Llama-4-Scout-109B	Q4_K_M	macOS	Apple M3 Max	64 GB	Apple GPU	86	48.2	95%	1,876
07	Qwen3-80B-A3B	Q4_K_M	Windows	Intel Core Ultra 7	64 GB	NVIDIA RTX 4080	84	35.8	95%	218
08	DeepSeek-V3-0324	Q5_K_M	Linux	AMD Ryzen 9 7950X	64 GB	NVIDIA RTX 4090	82	42.1	96%	943
09	Qwen3.5-35B-A3B	Q4_K_M	Windows	AMD Ryzen AI 9 HX	64 GB	AMD Radeon 890M	79	52.1	92%	820
10	Qwen3-80B-A3B	Q3_K_M	macOS	Apple M3 Pro	36 GB	Apple GPU	72	15.1	86%	287

▌ signeded25519·▌ anonymoushardware hash·▌ source

Five Rankings

ModelIndex combines five independent rankings. Each one answers a different question, so you always start from the lens that fits your decision.

Overall Score

“How good is this model overall?”

Composite 0-100 score weighted by accuracy (40%), speed (25%), time-to-first-token (15%), and user ratings (20%).

Hardware Match

“Which model performs best on my exact setup?”

Ranked models per hardware profile -- Apple Silicon, Intel, AMD, NVIDIA -- grouped by CPU, RAM tier, and GPU type.

Quantization Index

“Which quantization gives the best tradeoff?”

Speed vs accuracy per quantization variant (Q2_K through F16) per RAM tier.

Pair Ranking

“Which two models work best together?”

Primary + Secondary model pair rankings, made possible because runs two models in concert via the Intelligence Nucleus. Toggle the leaderboard above to Pairs to see it in action.

Domain Fitness

“Which model is best for finance? For email? For code?”

Domain-specific rankings across Finance, Mail, Chat, Code, Research, and Creative tasks.