family member

Qwen 3.6 35B-A3B

Ran on 1 kind of machine here, but its speed was not recorded. OpenRouter sells it at $0.90 per million output tokens.

1 build of Qwen 3.6 35B-A3B, 1 signed run on real machines: different packagers, precisions and engines, each a different file with its own numbers.

4Kcontext proved by recall

1provider 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. 1 provider has measured Qwen 3.6 35B-A3B 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 · 1 build

proved 4K context, by unsloth IQ1_M

How far back it remembers, machine by machine

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

machine · build	4K	why it stopped
Gram ·662a4e Linux, CPU only · 4 CPUs · IQ1_M by unsloth		4K 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

Gram ·662a4e1.1 kg8.56 J/tok · modelled

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

Gram ·662a4e1 run

proved by at least one build: Tool calling · Faithful to tool results · Chained tool calls · Structured output · Sustained output · Extended thinking · 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.

build	engine	whose work	memory	context proved	best tok/s	machines
IQ1_M by unslothunsloth/Qwen3.6-35B-A3B-GGUF:IQ1_M	ollama	quantizer · unsloth	—	4K	—	1

derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.

Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved3 builds measured Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF2 builds measured Qwen3.6-35B-A3B-abliterated-v4not measured Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressivenot measured Qwen3.6-35B-A3B-oQ4e-mtpnot measured Qwen3.6-35B-A3B-uncensored-hereticnot measured Qwen3.6-35B-A3B-BE-GGUFnot measured Qwen3.6-35B-A3B-NVFP4-Fastnot measured Qwen3.6-35B-A3B-MTP-GGUFnot measured