Forge-1-Mini-GGUF

Forge-1-Mini-GGUF · Q2_K · by North-ML1

hf.co/North-ML1/Forge-1-Mini-GGUF:Q2_K

North-ML1 · Q2_K · on ollama · derivative build

A change to forge-1-mini by somebody other than its vendor. Nothing the vendor proved carries over; every number here was measured on these weights.

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 29 Oct 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 declared512what the runtime reported. A node attests it was told this; nobody attests it is true.

context proved by recallnot probedthe 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.

Both numbers are needed to state a gap, and one of them is missing.

Languages, proved

None of the 10 languages asked came back correctly.

Each question was put entirely in its own language and script, and the answer had to be right. A model with no coverage cannot parse the question, so answering in English is a failure here, not a pass. 0 proved of 10 asked — a language absent from the probe set was never asked, and is not a claim either way.

Capabilities, measured

Speech outprobed, and failed

The model itself turned text into audio — identified from the container bytes, not from what the engine labelled them, so an error page announced as audio cannot pass. Distinct from this gram running a separate text-to-speech engine: an operator choosing between them is choosing between two architectures.

Reasons about codeprobed, and failed

Asked to predict exactly what a short program prints. This is the half of coding that matters for agent work and that writing valid syntax does not demonstrate: following state through control flow.

Writes codeprobed, and failed

Asked for a specific function and checked with the Go compiler’s own parser. Nothing is executed — running model-written code to score a model would be a security hole opened for a metric — but syntactic validity is a fact rather than an opinion.

Embeddingsprobed, and failed

The engine was asked for an embedding of a short text and returned a real, non-zero vector.

Follows instructionsprobed, and failed

Given a plain constraint on its output format and checked for exact obedience. This separates an instruct-tuned model from a base one — a base model answers fluently and ignores every instruction, which then looks like a dozen unrelated weaknesses instead of one.

Sustained outputprobed, and failed

Asked to produce a long structured answer and checked for length. A model that stops after a couple of hundred tokens cannot write a report, however capable it is otherwise.

Structured outputprobed, and failed

The ENGINE was asked to constrain decoding to a schema, and the answer conformed. This is stronger than politely asking for JSON and hoping: the grammar makes invalid output unreachable, which is what an operator actually builds on.

Extended thinkingprobed, and failed

The model emitted reasoning on the engine’s dedicated reasoning channel before answering. Read from that channel rather than by scanning the answer for tags, which is why models that reason are no longer reported as models that do not.

Synthesises sourcesprobed, and failed

Given three documents with one fact split across them, and required to combine rather than quote. No single document contains the answer, so a model that retrieves without reasoning cannot pass.

Tool callingprobed, and failed

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.

Visionprobed, and failed

A four-digit code was rendered into an image and the model had to read it back. A model that cannot see cannot guess four digits, and a model that can has no reason to fail — so this passes and fails for the right reason, which describing a picture never did.

Tool loop finishedprobed, and failed

Whether the conversation ENDED after the tool call, or the model kept calling until the turn budget ran out. Passing “tool calling” and failing this means the model will call a tool in production and never come back. A model chosen on the first flag alone is the reason an agent silently stops delivering work.

Audioprobed, and failed

Given audio and asked to transcribe it.

Faithful to tool resultsprobed, and failed

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.

Other builds of Forge-1-Mini-GGUF

every other build of this member measured on the network — compare what each actually proved

hf.co/North-ML1/Forge-1-Mini-GGUF:Q3_K_MNorth-ML1 · Q3_K_M · ollama

ctx not probed1 node

signed by this network

What machines here proved

peak throughput ever signed1074.92 tok/s · did:epn:002408…e3654f

resident while loaded0.0 GiB · did:epn:002408…e3654f

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 declared512

parameters5.19M

parameter count51,89,568

quantisationQ2_K

familyllama

formatgguf

ollama /api/show; the node attests that the runtime reported these, not that they are true. Attested by did:epn:002408…e3654f.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

North Charleston, South Carolina29415 · 1 node

Measured by

ranked on the provider standings

e3Gram ·e3654fP7

The machine that measured it

nothing is averaged — the machine is what you are choosing

did:epn:002408…e3654fNorth Charleston · 29415 · 0.40.11 · on host · 26 Oct 2026

0ctx provedthe model lost the needle at 4K

1074.92tok/s now50 samples · 1s0.0 GiB resident · 0.0 GiB on disk

✗ Speech out✗ Reasons about code✗ Writes code✗ Embeddings✗ Follows instructions✗ Sustained output✗ Structured output✗ Extended thinking✗ Synthesises sources✗ Tool calling✗ Vision✗ Tool loop finished✗ Audio✗ Faithful to tool results

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 512. 1 walk ended because the model forgot, 0 because the machine could not hold the prompt.

machine · build	4K	why it stopped
Gram ·e3654f Linux, CPU only · 4 CPUs · Q2_K by North-ML1		— the model lost the needle at 4K

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 ·e3654f3 g0.03 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.

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.