family member
Qwen 3.6 logo

Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF

2 builds of Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF, 3 signed runs on real machines: different packagers, precisions and engines, each a different file with its own numbers.

5.0tok/s, fastest machine
4Kcontext proved by recall
15.0 GBmemory, smallest build
2providers measured it
Run it on your gram Install a gram with one command. It works through the catalog on your own machine and signs every result. 2 providers have measured Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF so far.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.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 · 2 builds

trained 256K · proved 4K context, by huihui-ai Q6_K

5.0 tok/s peak, by huihui-ai Q2_K

What it fits on

The smallest build needs about 15.0 GB; 8 of 18 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. Mac, CPU only · 8 CPUs8 GB RAMnone
  9. NVIDIA GeForce RTX 3080 Ti12 GB on the cardnone
  10. Tesla T415 GB on the cardnone
  11. Intel(R) UHD Graphics 73016 GB RAM1 of 2
  12. Intel(R) Iris(R) Xe Graphics16 GB RAM1 of 2
  13. Apple M416 GB RAM1 of 2
  14. Apple M116 GB RAM1 of 2
  15. NVIDIA L422 GB on the card1 of 2
  16. 2× Tesla T429 GB on the card1 of 2
  17. Linux, CPU only · 4 CPUs31 GB RAM1 of 2
  18. 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. 1 walk ended because the model forgot, 2 because the machine could not hold the prompt.

machine · build4Kwhy it stopped
Gram ·4e94b2Linux, CPU only · 4 CPUs · Q6_K by huihui-ai4K too slow to answer here
Gram ·e3654fLinux, CPU only · 4 CPUs · Q6_K by huihui-ai4K too slow to answer here
Gram ·4e94b2Linux, CPU only · 4 CPUs · Q2_K by huihui-ai— the model lost the needle at 4K

Carbon per million tokens

Lowest build on each machine · 0 of 2 read off a power sensor, the rest modelled from the parts · fewer grams is better

  1. Gram ·e3654f532 g8.99 J/tok · modelled
  2. Gram ·4e94b2653 g6.12 J/tok · modelled

Carbon is location-based: signed energy × the yearly average of the grid where the machine signed its place (EU grid average (applied to NL) · 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 · Multiple images at once · 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
Q6_K by huihui-aihf.co/huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF:Q6_Ksafety removedollamaderivative · huihui-ai32.4 GB4K4.32
Q2_K by huihui-aihf.co/huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF:Q2_Ksafety removedollamaderivative · huihui-ai15.0 GB—5.01