family member
GLM-4.5 logo

GLM-4.5-DRAFT-0.6B-v3.0

140 tokens a second on Mac · Apple M4 · 10 CPUs · 16 GB RAM. No hosted API sells it, so this network is the place to run it.

1 build of GLM-4.5-DRAFT-0.6B-v3.0, 1 signed run on real machines: different packagers, precisions and engines, each a different file with its own numbers.

140tok/s, fastest machine
$1.40per M tokens · no API sells it
0.5 GBmemory, smallest build
1provider measured it
best on ollama · 1 build

no context proved on this engine yet

139.5 tok/s peak, by mradermacher IQ1_S

What it fits on

The smallest build needs about 0.5 GB; 16 of 16 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. NVIDIA GeForce RTX 3050 Laptop GPU4 GB on the cardevery build
  2. NVIDIA GeForce GTX 16504 GB on the cardevery build
  3. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAMevery build
  4. Windows, CPU only · 12 CPUs7 GB RAMevery build
  5. Apple silicon8 GB RAMevery build
  6. Apple M18 GB RAMevery build
  7. Mac, CPU only · 8 CPUs8 GB RAMevery build
  8. NVIDIA GeForce RTX 3080 Ti12 GB on the cardevery build
  9. Intel(R) UHD Graphics 73016 GB RAMevery build
  10. Intel(R) Iris(R) Xe Graphics16 GB RAMevery build
  11. Apple M416 GB RAMevery build
  12. Apple M116 GB RAMevery build
  13. NVIDIA L422 GB on the cardevery build
  14. 2× Tesla T429 GB on the cardevery build
  15. Linux, CPU only · 4 CPUs31 GB RAMevery build
  16. 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 · trained for 32K. 1 walk ended because the model forgot, 0 because the machine could not hold the prompt.

machine · build4Kwhy it stopped
nitin singhApple M4 · IQ1_S by mradermacher— the model lost the needle at 4K

Carbon per million tokens

Lowest build on each machine · 0 of 1 read off a power sensor, the rest modelled from the parts · fewer grams is better

  1. nitin singh35 g0.18 J/tok · modelled

Carbon is location-based: signed energy × the yearly average of the grid where the machine signed its place (India grid average; 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

proved by at least one build: Structured output · Sustained output

Every build

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

buildenginewhose workmemorycontext provedbest tok/smachines
IQ1_S by mradermacherhf.co/mradermacher/GLM-4.5-DRAFT-0.6B-v3.0-i1-GGUF:IQ1_Sollamaderivative · mradermacher0.5 GB—139.51

Compared on the same machine