/inferences/qwen-2-5/0.5b/qwen-q4_k_m-ollama-468a4ed0

hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:q4_k_m

Qwen · Q4_K_M · on ollama · vendor build

Measured by 5 nodes on hardware we do not own, and signed by each of them. What machines here actually proved — never what the card claims.

matrix built 24 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 declared32,768what the runtime reported. A node attests it was told this; nobody attests it is true.
context proved by recall32,768the 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.
A machine here made it use everything the runtime declared.
recalled 32k⌐ declared 32k · unsigned
every machine that timed it
239.1 tok/s · NVIDIA · Washington119.8 tok/s · unnamed machine39.7 tok/s · x86 · CPU · Hyderabad10.6 tok/s · unnamed machine5.8 tok/s · unnamed machine
5.8 → 239.1 tok/s across 5 machines · ×41.6 spreadNVIDIAunnamed machinex86 · CPU

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.

Languages, proved

EnglishKannada

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. 2 proved of 10 asked — a language absent from the probe set was never asked, and is not a claim either way.

Capabilities, measured

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 codepassed
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.
Follows instructionspassed
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 outputpassed
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 outputpassed
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 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.
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.

Other builds of Qwen2.5 0.5B Instruct

every other build of this member measured on the network — compare what each actually proved
qwen2.5:0.5bollama · ollama
ctx not probed1 node
signed by this network

What machines here proved

context proved by recall32,768
peak throughput ever signed239.08 tok/s · did:epn:002408…a5be46
resident while loaded3.7 GiB · did:epn:002408…2e5c02
machines that measured it5
samples behind those numbers5
regions it was proved in5
Every line traces to a node signature.
from the public record · unsigned

What the runtime says about it

context declared32,768
parameters630M
parameter count63,01,67,424
quantisationQ4_K_M
familyqwen2
formatgguf
ollama /api/show; the node attests that the runtime reported these, not that they are true. Attested by did:epn:002408…a5be46.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

The Dalles, Oregon97058 · 1 node
Bhubaneswar, Odisha752115 · 1 node
Bengaluru, Karnataka562130 · 1 node
Vikarabad, Telangana501202 · 1 node
North 24 Parganas, West Bengal700108 · 1 node

Every machine that measured it

nothing is averaged — the machine is what you are choosing
did:epn:002408…a5be46The Dalles · 97058 · 0.40.6 · on host · 19 Oct 2026Intel Xeon @ 2.00GHz · Tesla T4 15 GiB · 2 cores · 31.3 GiB RAM
32,768ctx provedrecalled at every size asked
239.08tok/s now62 samples · 52s0.9 GiB resident · 0.9 GiB on card · 0.5 GiB on disk
✗ Reasons about code✓ Writes code✓ Follows instructions✗ Sustained output✓ Structured output✗ Extended thinking✗ Synthesises sources✓ Tool calling✓ Faithful to tool results✓ Tool loop finished✗ Chained tool calls✗ Vision✗ Audio✓ 1 languages
did:epn:002408…84bf54Bhubaneswar · 752115 · 0.34.0 · 30 Sept 2026
0ctx provedno recall at 4,096
119.75tok/s now88 samples · 36s0.5 GiB resident · 0.5 GiB on card · 0.5 GiB on disk
✗ Reasons about code✗ Writes code✗ Follows instructions✗ Sustained output✗ Structured output✗ Extended thinking✗ Synthesises sources✗ Tool calling✗ Tool loop finished✗ Vision✗ Audio✗ Faithful to tool results
did:epn:002408…9e3c79Bengaluru · 562130 · 24 Oct 2026Intel64 Family 6 Model 151 Stepping 5, GenuineIntel · 15.7 GiB RAM
—ctx proved
39.65tok/s now10 samples · 5s2.1 GiB resident · 0.5 GiB on disk · 25.2s cold start
no capability probed
did:epn:002408…2e5c02Vikarabad · 501202 · 0.32.5 · 8 Oct 2026
16,384ctx provedprobe ew/bopIFD9…
10.57tok/s nowpeak 31.15 · 17 Sept 202675 samples · 1,065s3.7 GiB resident · 0.5 GiB on disk · 19.0s cold start
✗ Reasons about code✗ Sustained output✓ Structured output✗ Synthesises sources✓ Tool calling✓ Faithful to tool results✓ Tool loop finished✗ Chained tool calls✗ Extended thinking✗ Vision✗ Audio✓ 1 languages
did:epn:002408…9a1db0North 24 Parganas · 700108 · 0.34.0 · 16 Sept 2026
0ctx provedno recall at 1,31,072 · 65,536 · 32,768 · 16,384 · 8,192 · 4,096
5.75tok/s now2 samples · 9s0.5 GiB resident · 0.5 GiB on card · 0.5 GiB on disk
✗ Reasons about code✗ Writes code✗ Follows instructions✗ Sustained output✓ Structured output✗ Extended thinking✗ Synthesises sources✗ Tool calling✗ Tool loop finished✗ Vision✗ Audio✗ Faithful to tool results✓ 1 languages

Context ladders attempted: did:epn:002408…a5be46 4096,8192,16384,32768 · did:epn:002408…84bf54 4096 · did:epn:002408…2e5c02 131072,65536,32768,16384,8192,4096 · did:epn:002408…9a1db0 131072,65536,32768,16384,8192,4096

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.