build

Q4_K_M · by maziyarpanahi

hf.co/MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF:Q4_K_M

maziyarpanahi · Q4_K_M · on ollama

Measured by one node on hardware we do not own, and signed by each of them. What machines here actually proved — never what the card claims.

matrix built 8 Nov 2026 · every field verified against the signature of the node that produced it, and re-verifiable by you: each signed figure carries the exact bytes the node signed (signing_payload_b64) and the signature over them, and the ed25519 public key is embedded in node_did. effective_ctx is the context length a node PROVED by recall, never the length a model card advertises
context declared128Kwhat the runtime reported. A node attests it was told this; nobody attests it is true.
context proved by recall4Kthe largest size at which a machine could still find tokens planted across the whole prompt — start, middle and end, all of which had to come back.
Advertises 32× the context any machine here could make it use.Not an accusation — it is what happened here, and it is signed.
recalled 4k⌐ declared 128k · unsignedadvertises 32× what it proved

Capabilities, measured

Embeddingsprobed, and failed
The engine was asked for an embedding of a short text and returned a real, non-zero vector.
Tool callingpassed
The node asked the model to call a function and checked that it called the RIGHT one with a well-formed argument — not merely that it emitted a tool name.
Faithful to tool resultspassed
The model was handed a list through a tool and had to report every item back. Calling a tool and understanding its answer are different abilities: a model can produce a perfect call, receive nine items, and confidently report three. This is the flag that separates them.
Tool loop finishedpassed
Whether the conversation ENDED after the tool call, or the model kept calling until the turn budget ran out. A model that passes tool calling and fails this will call a tool in production and never come back.
Chained tool callsprobed, and failed
The model had to call one tool, read its answer, and call a second with a value derived from it. One call is not agentic work — real specialist jobs are sequences, and a model that never takes the second step looks, from outside, exactly like a specialist silently doing nothing.
Structured outputprobed, and failed
Asked for JSON matching a schema, and got it. This is the difference between a model you can build on and one you must parse defensively.
Extended thinkingprobed, and failed
The model emits reasoning before its answer. Measured where the probe could observe it.
Visionprobed, and failed
Shown an image and asked what was in it. The node checked the answer.
Audioprobed, and failed
Given audio and asked to transcribe it.
signed by this network

What machines here proved

context proved by recall4K
peak throughput ever signed78.03 tok/s · did:epn:002408…84bf54
resident while loaded4.6 GiB (4.6 on card) · did:epn:002408…84bf54
machines that measured it1
samples behind those numbers1
regions it was proved in1
Every line traces to a node signature.
from the public record · unsigned

What the runtime says about it

context declared128K
parameters3.21B
parameter count3,21,27,49,888
quantisationQ4_K_M
familyllama
formatgguf
ollama /api/show; the node attests that the runtime reported these, not that they are true. Attested by did:epn:002408…84bf54.The only unsigned block on this page. We attest we read these from the runtime — not that they are true. Nobody signs a model card.

Proven across regions

Khordha, Odisha752101 · 1 node

Measured by

ranked on the provider standings

The machine that measured it

nothing is averaged — the machine is what you are choosing
did:epn:002408…84bf54Khordha · 752101 · 0.34.0 · on pod · 8 Nov 2026AMD Ryzen 7 5800X 8-Core · RTX 3080 Ti 12 GiB · 15.9 GiB RAM
4Kctx provedthis machine could not serve at 8K
78.03tok/s now18 samples · 5s4.6 GiB resident · 4.6 GiB on card · 1.9 GiB on disk
✗ Embeddings✓ Tool calling✓ Faithful to tool results✓ Tool loop finished✗ Chained tool calls✗ Structured output✗ Extended thinking✗ Vision✗ Audio

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 128K. 0 walks ended because the model forgot, 1 because the machine could not hold the prompt.

machine · build4K8Kwhy it stopped
Kunal HindochaNVIDIA GeForce RTX 3080 Ti · Q4_K_M by maziyarpanahi4K this machine could not serve at 8K

Carbon per million tokens

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

  1. Kunal Hindocha1.3 kg6.57 J/tok · sensor

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.

Run this where your data already is

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

Run a gramPut a machine on the network in this region; it signs its capacity into the room.Open a gramxStart your own room — an org, a community, a brand.Be invitedAccept a link from an admin to cross into the private room.