Where do these figures come from?

Each field is synced from the project's own registry and carries the source that reported it and the moment it was observed. Values that fail validation are withheld rather than shown.

How current is this data?

The last sync completed 3h ago. Every field shows its own observation date, because fields refresh independently.

Local inference hardware

This directory tracks 10 GPUs, accelerators and SoCs used for local model inference, with VRAM, memory bandwidth, power draw and list price. Specifications are curated by hand from vendor datasheets and carry the date a person last checked them; fabrication details are read from Wikipedia. Every figure shows which of the two it is.

Live

74 fields

wikitext: 19/19 current; 3h

Moved since last reading

Nothing changed between the last two readings.

Stars from Wikipedia infobox. Movement is measured between two real observations; values that failed validation are withheld rather than shown.

Machines: 10
VRAM catalogued: 792
With a listed price: 5/10
Last sync: 3h agosucceeded

RTX A6000VRAM, GB48editorial · 1mo agoInstinct MI300XVRAM, GB192editorial · 1mo agoRadeon RX 7900 XTXVRAM, GB24editorial · 1mo agoApple M4 ProVRAM, GB64editorial · 1mo agoApple M2 UltraVRAM, GB192editorial · 1mo agoApple M3 MaxVRAM, GB128editorial · 1mo agoH100 PCIeVRAM, GB80editorial · 1mo agoGeForce RTX 3090VRAM, GB24editorial · 1mo agoGeForce RTX 4080 SuperVRAM, GB16editorial · 1mo agoGeForce RTX 4090VRAM, GB24editorial · 1mo ago

SortVRAM Bandwidth Power draw Name

No hiring column here. The job-board classifier extracts framework names, so the join can only speak about frameworks — for these entities we have not measured demand, rather than measured it to be zero.

5 GPUs, accelerators and SoCs, sorted by vram. Each row shows the last time the ranked figure was observed.
Machine	VRAM, GB	GB/s	TDP, W	MSRP	Class	Checked
H100 PCIeNVIDIA	80	2,039	350	not listed	datacenter	Aging1mo ago
RTX A6000NVIDIA	48	768	300	4,650	workstation	Aging1mo ago
GeForce RTX 3090NVIDIA	24	936	350	1,499	gpu	Aging1mo ago
GeForce RTX 4090NVIDIA	24	1,008	450	1,599	gpu	Aging1mo ago
GeForce RTX 4080 SuperNVIDIA	16	736	320	999	gpu	Aging1mo ago

3 of 3 machines selected

Compare Clear

Source: Wikipedia infobox. Every value carries the moment it was observed; figures that failed validation are withheld rather than shown. SLA: current within 720h, ageing to 2160h, stale beyond 4320h.

indexable · canonical /data/hardware?vendor=nvidia

Also tracked

Other datasets

Same engine, same provenance rules — every figure carries the source that reported it and when.

Local inference hardware

Other datasets

Smoke dataset

Agent engineering frameworks

Language and embedding models