family member
Qwen 3.6 logo

Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved

1 build of Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved, 1 signed run on real machines: different packagers, precisions and engines, each a different file with its own numbers.

4.9tok/s, fastest machine
4Kcontext proved by recall
24.3 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 Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved; 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 ollama · 1 build

trained 256K · proved 4K context, by llmfan46 Q4_K_M

4.9 tok/s peak, by llmfan46 Q4_K_M

What it fits on

The smallest build needs about 24.3 GB; 3 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 cardnone
  3. NVIDIA GeForce GTX 16504 GB on the cardnone
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAMnone
  5. Windows, CPU only · 12 CPUs7 GB RAMnone
  6. Apple silicon8 GB RAMnone
  7. Apple M18 GB RAMnone
  8. NVIDIA GeForce RTX 3080 Ti12 GB on the cardnone
  9. Tesla T415 GB on the cardnone
  10. Intel(R) UHD Graphics 73016 GB RAMnone
  11. Intel(R) Iris(R) Xe Graphics16 GB RAMnone
  12. Apple M416 GB RAMnone
  13. Apple M116 GB RAMnone
  14. NVIDIA L422 GB on the cardnone
  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 · trained for 256K. 0 walks ended because the model forgot, 1 because the machine could not hold the prompt.

machine · build4Kwhy it stopped
Gram ·4e94b2Linux, CPU only · 4 CPUs · Q4_K_M by llmfan464K too slow to answer here

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. Gram ·4e94b21.3 kg12.47 J/tok · modelled

Carbon is location-based: signed energy × the yearly average of the grid where the machine signed its place (United States 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: Tool calling · Structured output · Sustained output · Extended thinking · Vision · Counts in images · Spatial reasoning · Writes code · Reasons about code · Synthesises sources · Follows instructions

Every build

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

buildenginewhose workmemorycontext provedbest tok/smachines
Q4_K_M by llmfan46hf.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-GGUF:Q4_K_Msafety removedollamaderivative · llmfan4624.3 GB4K4.91