family member
GLM-4.5 logo

GLM-4.5-Air-0.72B-MTP

Ran on 1 kind of machine here, but its speed was not recorded.

1 build of GLM-4.5-Air-0.72B-MTP, 1 signed run on real machines: different packagers, precisions and engines, each a different file with its own numbers.

1.6 GBmemory, smallest build
1provider measured it
Use it in your own room Ask Evo in your gramx and it runs on a machine that proved it. On your own machines it costs you nothing.Measure it on your machine A gram works through the catalog by itself and signs every result. 1 provider has measured GLM-4.5-Air-0.72B-MTP; every run is a point on the providers board.Compare every build Put it beside every other model in one table: speed, price, context and the API price, one row each.
best on vllm · 1 build

no context proved on this engine yet

What it fits on

The smallest build needs about 1.6 GB; 16 of 17 kinds of machine on the network can hold it. Bars: each kind's memory (its card's, else RAM) · ticks: every build, at the size it held plus a fifth for the prompt.

  1. Linux, CPU only · 2 CPUs1 GB RAMnone
  2. NVIDIA GeForce RTX 3050 Laptop GPU4 GB on the cardevery build
  3. NVIDIA GeForce GTX 16504 GB on the cardevery build
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAMevery build
  5. Windows, CPU only · 12 CPUs7 GB RAMevery build
  6. Apple silicon8 GB RAMevery build
  7. Apple M18 GB RAMevery build
  8. NVIDIA GeForce RTX 3080 Ti12 GB on the cardevery build
  9. Tesla T415 GB on the cardevery build
  10. Intel(R) UHD Graphics 73016 GB RAMevery build
  11. Intel(R) Iris(R) Xe Graphics16 GB RAMevery build
  12. Apple M416 GB RAMevery build
  13. Apple M116 GB RAMevery build
  14. NVIDIA L422 GB on the cardevery build
  15. 2× Tesla T429 GB on the cardevery build
  16. Linux, CPU only · 4 CPUs31 GB RAMevery build
  17. NVIDIA RTX PRO 6000 Blackwell Server Edition95 GB on the cardevery build

How far back it remembers, machine by machine

Filled: the needle came back at that prompt size · outlined: asked and lost · blank: not asked. 1 walk ended because the model forgot, 0 because the machine could not hold the prompt.

machine · build4Kwhy it stopped
Amit KhetanNVIDIA L4 · BF16 by nm-testing— the model lost the needle at 4K

Carbon per million tokens

Lowest build on each machine · 1 of 1 read off a power sensor, the rest modelled from the parts · fewer grams is better

  1. Amit Khetan76 g0.58 J/tok · sensor

Carbon is location-based: signed energy × the yearly average of the grid where the machine signed its place (world grid average (Singapore not in the table); Ember Global Electricity Review 2025 (2024 generation), location-based). Facility overhead is not included. A machine on its own solar is not credited until it can prove it.

Measured by

The people whose machines signed these numbers

Every build

Each its own file with its own page: the machines that ran it and their signatures.

buildenginewhose workmemorycontext provedbest tok/smachines
BF16 by nm-testingnm-testing/GLM-4.5-Air-0.72B-MTPvllmderivative · nm-testing1.6 GB——1