← All models

qwen3:0.6b

Measured by one node on hardware we do not own, and signed by each of them.

Context declared

40,960

what the runtime reported. A node attests it was told this; nobody attests that it is true.

Context proved by recall

4,096

the largest size at which a machine could still find a token planted at the far end.

This model advertises 10× the context any machine on this network could make it use. That is not an accusation — a longer window may work on other hardware, at other quantisation. It is what happened here, and it is signed.

This model calls tools correctly and does not stop. A node watched it call the probe tool, then call it again, until the turn budget ran out. Chosen on “supports tools” alone, it will call a tool in production and never come back.

What the runtime declared

Quantisation

Q4_K_M

Parameters

751.63M

Family

qwen3

Format

gguf

ollama /api/show; the node attests that the runtime reported these, not that they are true. Attested by did:epn:002408…9e3c79.

Capabilities, measured

The machine that measured it

Nothing below is averaged. A model is fast on one machine and slow on another, and the machine is what you are choosing.

Run this where your data already is

Tell us the workload, whose machines it should run on, and which jurisdiction it answers to.

Scope your workload