MiniCPM-V 4 BASE
MiniCPM-V 4 BASE · Q4_K_M · by openbmb
hf.co/openbmb/MiniCPM-V-4-gguf:Q4_K_M
openbmb · Q4_K_M · on ollama · vendor build
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 28 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 advertisescontext declared32Kwhat 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.
Capabilities, measured
Embeddingsprobed, and failed
The engine was asked for an embedding of a short text and returned a real, non-zero vector.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.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.Counts in imagespassed
Shown a row of shapes and asked how many. Reading rendered text and grasping a scene are different abilities, and a model can do the first with no spatial understanding at all — which is what charts, shelf photographs and document layout actually need.Visionpassed
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.signed by this networkEvery line traces to a node signature.
What machines here proved
peak throughput ever signed4.91 tok/s · did:epn:002408…d061c9
machines that measured it1
samples behind those numbers1
regions it was proved in1
from the public record · unsignedollama /api/show; the node attests that the runtime reported these, not that they are true. Attested by did:epn:002408…d061c9.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.
What the runtime says about it
context declared32K
parameters3.61B
parameter count3,60,58,34,240
quantisationQ4_K_M
familyllama
formatgguf
Proven across regions
Measured by
ranked on the provider standingsThe machine that measured it
nothing is averaged — the machine is what you are choosingdid:epn:002408…d061c9Bengaluru · 562130 · 0.34.0 · on host · 28 Oct 2026
0ctx provedthe model lost the needle at 4K
3.73tok/s nowpeak 4.91 · 28 Oct 20269 samples · 459s
✗ Embeddings✓ Structured output✗ Extended thinking✗ Tool calling✓ Counts in images✓ Vision✗ Tool loop finished✗ Audio✗ Faithful to tool results
Context ladders attempted: did:epn:002408…d061c9 4096
Run this where your data already is
Tell us the workload, whose machines it should run on, and which jurisdiction it answers to.